Technical transformation state
Transformation supported
Verified public open-weight release with authoritative checkpoint evidence.
Mistral / Mistral Small 4 119B A6B
Transformation options for Mistral Small 4 119B A6B
Validated per release from registry evidence, pricing components and runtime compatibility.
Architecture
Mistral3ForConditionalGeneration
119.00B parameters · 1048576 context
Supported transformations
quantization
Validated per release
runtime packaging
Validated per release
managed hosting
Validated per release
Distillation
Validated per release
gpu targeting
Validated per release
Evaluation and benchmarking
Validated per release
download
Validated per release
Published packages
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
FP8transformers Download packageHost with FusionPointAIDownload + host
USD 70,160.00
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
FP8GPU targeted2 × NVIDIA H200 SXM 141GBtransformersRuntime optimized Download packageHost with FusionPointAIDownload + host
USD 76,160.00
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
FP8GPU targeted2 × NVIDIA H100 SXM 80GBtransformersRuntime optimized Download packageHost with FusionPointAIDownload + host
USD 76,160.00
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
FP8GPU targeted2 × NVIDIA H100 PCIe 80GBtransformersRuntime optimized Download packageHost with FusionPointAIDownload + host
USD 76,160.00
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
FP8GPU targeted2 × NVIDIA A100 SXM 80GBtransformersRuntime optimized Download packageHost with FusionPointAIDownload + host
USD 76,160.00
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
GPU count: 4
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
FP8GPU targeted4 × NVIDIA l40stransformersRuntime optimized Download packageHost with FusionPointAIDownload + host
USD 76,160.00
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
GPU count: 7
Runtime packaging: transformers
Configured delivery: Download + host
Delivery options: Download package / Host with FusionPointAI / Download + host
FP8GPU targeted7 × NVIDIA L4transformersRuntime optimized Download packageHost with FusionPointAIDownload + host
USD 76,160.00
One-time engineering
Design validated
Mistral Small 4 119B A6B DISTILLATION Production Package - Quality-retention distillation
Mistral · Mistral Small 4 119B A6B
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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
DISTILLATIONQuality retentiontransformers Download packageHost with FusionPointAIDownload + host
USD 150,535.00
One-time engineering
Design validated
Mistral Small 4 119B A6B DISTILLATION Production Package - Throughput-optimized distillation
Mistral · Mistral Small 4 119B A6B
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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
DISTILLATIONThroughput optimizedtransformers Download packageHost with FusionPointAIDownload + host
USD 150,535.00
One-time engineering