Capability-driven
Top 100 Quantized Production Packages
Validated per release from registry evidence, pricing components and runtime compatibility.
Engineering ready
LongCat 2.0 INT8 Production Package - Downloadable production build
LongCat · LongCat 2.0
Package profile: Downloadable production build
Transformation operations: INT8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: sglang
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 105,600
One-time engineering
Engineering ready
LongCat 2.0 FP8 Production Package - Downloadable production build
LongCat · LongCat 2.0
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: sglang
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
MiMo-V2.5-Pro FP8 Production Package - Downloadable production build
MiMo · MiMo-V2.5-Pro
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: sglang
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
K-EXAONE 2.0 750B-A37B FP8 Production Package - GPU-targeted hosted production
EXAONE · K-EXAONE 2.0 750B-A37B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
K-EXAONE 2.0 750B-A37B FP8 Production Package - Downloadable production build
EXAONE · K-EXAONE 2.0 750B-A37B
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
GLM-5 FP8 Production Package - GPU-targeted hosted production
GLM · GLM-5
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
GLM-5 FP8 Production Package - Downloadable production build
GLM · GLM-5
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
GLM-5.1 FP8 Production Package - GPU-targeted hosted production
GLM · GLM-5.1
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
GLM-5.1 FP8 Production Package - Downloadable production build
GLM · GLM-5.1
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
GLM-5.2 FP8 Production Package - GPU-targeted hosted production
GLM · GLM-5.2
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
GLM-5.2 FP8 Production Package - Downloadable production build
GLM · GLM-5.2
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
Mistral Large 3 675B Instruct 2512 FP8 Production Package - GPU-targeted hosted production
Mistral · Mistral Large 3 675B Instruct 2512
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: vllm
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Mistral Large 3 675B Instruct 2512 FP8 Production Package - Downloadable production build
Mistral · Mistral Large 3 675B Instruct 2512
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: vllm
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
DeepSeek V3.1 FP8 Production Package - GPU-targeted hosted production
DeepSeek · DeepSeek V3.1
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
DeepSeek V3.1 FP8 Production Package - Downloadable production build
DeepSeek · DeepSeek V3.1
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
DeepSeek V3.2 FP8 Production Package - GPU-targeted hosted production
DeepSeek · DeepSeek V3.2
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
DeepSeek R1 FP8 Production Package - GPU-targeted hosted production
DeepSeek · DeepSeek R1
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
DeepSeek V3.2 Speciale FP8 Production Package - GPU-targeted hosted production
DeepSeek · DeepSeek V3.2 Speciale
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
DeepSeek V3.2 FP8 Production Package - Downloadable production build
DeepSeek · DeepSeek V3.2
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
DeepSeek R1 FP8 Production Package - Downloadable production build
DeepSeek · DeepSeek R1
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
DeepSeek V3.2 Speciale FP8 Production Package - Downloadable production build
DeepSeek · DeepSeek V3.2 Speciale
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
DeepSeek R1 0528 FP8 Production Package - GPU-targeted hosted production
DeepSeek · DeepSeek R1 0528
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
DeepSeek R1 0528 FP8 Production Package - Downloadable production build
DeepSeek · DeepSeek R1 0528
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
GLM-5.3-Flash FP8 Production Package - GPU-targeted hosted production
GLM · GLM-5.3-Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 6
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
GLM-5.3-Flash FP8 Production Package - GPU-targeted hosted production
GLM · GLM-5.3-Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 6
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
GLM-5.3-Flash FP8 Production Package - GPU-targeted hosted production
GLM · GLM-5.3-Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 6
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
GLM-5.3-Flash FP8 Production Package - GPU-targeted hosted production
GLM · GLM-5.3-Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 3
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
GLM-5.3-Flash FP8 Production Package - Downloadable production build
GLM · GLM-5.3-Flash
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
MiMo-V2.5 FP8 Production Package - GPU-targeted hosted production
MiMo · MiMo-V2.5
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 6
Runtime packaging: sglang
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
MiMo-V2.5 FP8 Production Package - GPU-targeted hosted production
MiMo · MiMo-V2.5
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 6
Runtime packaging: sglang
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
MiMo-V2.5 FP8 Production Package - GPU-targeted hosted production
MiMo · MiMo-V2.5
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 6
Runtime packaging: sglang
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
MiMo-V2.5 FP8 Production Package - GPU-targeted hosted production
MiMo · MiMo-V2.5
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 3
Runtime packaging: sglang
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
MiMo-V2.5 FP8 Production Package - Downloadable production build
MiMo · MiMo-V2.5
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: sglang
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
Command A+ 05-2026 FP8 Production Package - GPU-targeted hosted production
Command A · Command A+ 05-2026
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 6
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Command A+ 05-2026 FP8 Production Package - GPU-targeted hosted production
Command A · Command A+ 05-2026
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Command A+ 05-2026 FP8 Production Package - GPU-targeted hosted production
Command A · Command A+ 05-2026
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Command A+ 05-2026 FP8 Production Package - GPU-targeted hosted production
Command A · Command A+ 05-2026
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Command A+ 05-2026 FP8 Production Package - GPU-targeted hosted production
Command A · Command A+ 05-2026
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 3
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Command A+ 05-2026 FP8 Production Package - Downloadable production build
Command A · Command A+ 05-2026
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
Step 3.7 Flash FP8 Production Package - GPU-targeted hosted production
StepFun · Step 3.7 Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 6
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Step 3.7 Flash FP8 Production Package - GPU-targeted hosted production
StepFun · Step 3.7 Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Step 3.7 Flash FP8 Production Package - GPU-targeted hosted production
StepFun · Step 3.7 Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Step 3.7 Flash FP8 Production Package - GPU-targeted hosted production
StepFun · Step 3.7 Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Step 3.7 Flash FP8 Production Package - GPU-targeted hosted production
StepFun · Step 3.7 Flash
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 112,700
One-time engineering
Engineering ready
Step 3.7 Flash FP8 Production Package - Downloadable production build
StepFun · Step 3.7 Flash
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 106,700
One-time engineering
Engineering ready
Mistral Small 4 119B A6B FP8 Production Package - GPU-targeted hosted production
Mistral · Mistral Small 4 119B A6B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Mistral Small 4 119B A6B FP8 Production Package - GPU-targeted hosted production
Mistral · Mistral Small 4 119B A6B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Mistral Small 4 119B A6B FP8 Production Package - GPU-targeted hosted production
Mistral · Mistral Small 4 119B A6B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Mistral Small 4 119B A6B FP8 Production Package - GPU-targeted hosted production
Mistral · Mistral Small 4 119B A6B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Mistral Small 4 119B A6B FP8 Production Package - GPU-targeted hosted production
Mistral · Mistral Small 4 119B A6B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Mistral Small 4 119B A6B FP8 Production Package - GPU-targeted hosted production
Mistral · Mistral Small 4 119B A6B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Mistral Small 4 119B A6B FP8 Production Package - Downloadable production build
Mistral · Mistral Small 4 119B A6B
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 70,160
One-time engineering
Engineering ready
GLM-4.6V FP8 Production Package - GPU-targeted hosted production
GLM · GLM-4.6V
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 6
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
GLM-4.6V FP8 Production Package - GPU-targeted hosted production
GLM · GLM-4.6V
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 3
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
GLM-4.6V FP8 Production Package - GPU-targeted hosted production
GLM · GLM-4.6V
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
GLM-4.6V FP8 Production Package - GPU-targeted hosted production
GLM · GLM-4.6V
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
GLM-4.6V FP8 Production Package - GPU-targeted hosted production
GLM · GLM-4.6V
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
GLM-4.6V FP8 Production Package - GPU-targeted hosted production
GLM · GLM-4.6V
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
GLM-4.6V FP8 Production Package - Downloadable production build
GLM · GLM-4.6V
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 70,160
One-time engineering
Engineering ready
Qwen3 Coder Next FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3 Coder Next
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 5
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Qwen3 Coder Next FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3 Coder Next
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 3
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Qwen3 Coder Next FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3 Coder Next
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Qwen3 Coder Next FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3 Coder Next
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Qwen3 Coder Next FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3 Coder Next
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Qwen3 Coder Next FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3 Coder Next
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 76,160
One-time engineering
Engineering ready
Qwen3 Coder Next FP8 Production Package - Downloadable production build
Qwen · Qwen3 Coder Next
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 70,160
One-time engineering
Engineering ready
Qwen3-VL 32B Thinking FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Thinking
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Thinking FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Thinking
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Thinking FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Thinking
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Thinking FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Thinking
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Thinking FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Thinking
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Thinking FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Thinking
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Instruct FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Instruct
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Instruct FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Instruct
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Instruct FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Instruct
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Instruct FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Instruct
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Instruct FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Instruct
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Instruct FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3-VL 32B Instruct
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3-VL 32B Thinking FP8 Production Package - Downloadable production build
Qwen · Qwen3-VL 32B Thinking
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 28,400
One-time engineering
Engineering ready
Qwen3-VL 32B Instruct FP8 Production Package - Downloadable production build
Qwen · Qwen3-VL 32B Instruct
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 28,400
One-time engineering
Engineering ready
Qwen3.8 27B FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3.8 27B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3.8 27B FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3.8 27B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Qwen3.8 27B FP8 Production Package - GPU-targeted hosted production
Qwen · Qwen3.8 27B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Devstral Small 2 24B FP8 Production Package - GPU-targeted hosted production
Mistral · Devstral Small 2 24B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 2
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Devstral Small 2 24B FP8 Production Package - GPU-targeted hosted production
Mistral · Devstral Small 2 24B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Devstral Small 2 24B FP8 Production Package - GPU-targeted hosted production
Mistral · Devstral Small 2 24B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Devstral Small 2 24B FP8 Production Package - GPU-targeted hosted production
Mistral · Devstral Small 2 24B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Devstral Small 2 24B FP8 Production Package - GPU-targeted hosted production
Mistral · Devstral Small 2 24B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Devstral Small 2 24B FP8 Production Package - GPU-targeted hosted production
Mistral · Devstral Small 2 24B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Devstral Small 2 24B FP8 Production Package - Downloadable production build
Mistral · Devstral Small 2 24B
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 28,400
One-time engineering
Engineering ready
Step3-VL 10B FP8 Production Package - GPU-targeted hosted production
StepFun · Step3-VL 10B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Step3-VL 10B FP8 Production Package - GPU-targeted hosted production
StepFun · Step3-VL 10B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Step3-VL 10B FP8 Production Package - GPU-targeted hosted production
StepFun · Step3-VL 10B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Step3-VL 10B FP8 Production Package - GPU-targeted hosted production
StepFun · Step3-VL 10B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 PCIe 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Step3-VL 10B FP8 Production Package - GPU-targeted hosted production
StepFun · Step3-VL 10B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Step3-VL 10B FP8 Production Package - GPU-targeted hosted production
StepFun · Step3-VL 10B
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA H200 SXM 141GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Step3-VL 10B FP8 Production Package - Downloadable production build
StepFun · Step3-VL 10B
Package profile: Downloadable production build
Transformation operations: FP8 Quantization, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: transformers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 28,400
One-time engineering
Engineering ready
Ministral 3 8B Instruct 2512 FP8 Production Package - GPU-targeted hosted production
Mistral · Ministral 3 8B Instruct 2512
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L4 24GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Ministral 3 8B Instruct 2512 FP8 Production Package - GPU-targeted hosted production
Mistral · Ministral 3 8B Instruct 2512
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA L40S 48GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering
Engineering ready
Ministral 3 8B Instruct 2512 FP8 Production Package - GPU-targeted hosted production
Mistral · Ministral 3 8B Instruct 2512
Package profile: GPU-targeted hosted production
Transformation operations: FP8 Quantization, Runtime packaging, Evaluation and benchmarking
Target GPU: NVIDIA A100 SXM 80GB
GPU count: 1
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 34,400
One-time engineering