Capability-driven
Top 100 Distilled Production Packages
Validated per release from registry evidence, pricing components and runtime compatibility.
Design validated
Production distillation package for DeepSeek V4 Pro 0813 - Throughput-optimized distillation
DeepSeek · DeepSeek V4 Pro 0813
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek V4 Pro 0813 - Quality-retention distillation
DeepSeek · DeepSeek V4 Pro 0813
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
USD 240,363
One-time engineering
Design validated
Production distillation package for LongCat 2.0 - Throughput-optimized distillation
LongCat · LongCat 2.0
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for LongCat 2.0 - Quality-retention distillation
LongCat · LongCat 2.0
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for MiMo-V2.5-Pro - Throughput-optimized distillation
MiMo · MiMo-V2.5-Pro
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for MiMo-V2.5-Pro - Quality-retention distillation
MiMo · MiMo-V2.5-Pro
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for K-EXAONE 2.0 750B-A37B - Throughput-optimized distillation
EXAONE · K-EXAONE 2.0 750B-A37B
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
USD 240,363
One-time engineering
Design validated
Production distillation package for K-EXAONE 2.0 750B-A37B - Quality-retention distillation
EXAONE · K-EXAONE 2.0 750B-A37B
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
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-5 - Throughput-optimized distillation
GLM · GLM-5
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
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-5 - Quality-retention distillation
GLM · GLM-5
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
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-5.1 - Throughput-optimized distillation
GLM · GLM-5.1
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
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-5.1 - Quality-retention distillation
GLM · GLM-5.1
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
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-5.2 - Throughput-optimized distillation
GLM · GLM-5.2
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
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-5.2 - Quality-retention distillation
GLM · GLM-5.2
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Mistral Large 3 675B Instruct 2512 - Throughput-optimized distillation
Mistral · Mistral Large 3 675B Instruct 2512
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for Mistral Large 3 675B Instruct 2512 - Quality-retention distillation
Mistral · Mistral Large 3 675B Instruct 2512
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek V3.1 - Throughput-optimized distillation
DeepSeek · DeepSeek V3.1
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek V3.1 - Quality-retention distillation
DeepSeek · DeepSeek V3.1
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek V3.2 - Throughput-optimized distillation
DeepSeek · DeepSeek V3.2
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek V3.2 - Quality-retention distillation
DeepSeek · DeepSeek V3.2
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek R1 - Throughput-optimized distillation
DeepSeek · DeepSeek R1
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek R1 - Quality-retention distillation
DeepSeek · DeepSeek R1
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek V3.2 Speciale - Throughput-optimized distillation
DeepSeek · DeepSeek V3.2 Speciale
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek V3.2 Speciale - Quality-retention distillation
DeepSeek · DeepSeek V3.2 Speciale
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek R1 0528 - Throughput-optimized distillation
DeepSeek · DeepSeek R1 0528
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
USD 240,363
One-time engineering
Design validated
Production distillation package for DeepSeek R1 0528 - Quality-retention distillation
DeepSeek · DeepSeek R1 0528
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
USD 240,363
One-time engineering
Design validated
Production distillation package for MiniMax M1 80K - Throughput-optimized distillation
MiniMax · MiniMax M1 80K
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
USD 240,363
One-time engineering
Design validated
Production distillation package for MiniMax M1 80K - Quality-retention distillation
MiniMax · MiniMax M1 80K
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
USD 240,363
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 VL 424B-A47B - Throughput-optimized distillation
ERNIE · ERNIE 4.5 VL 424B-A47B
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 240,363
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 VL 424B-A47B - Quality-retention distillation
ERNIE · ERNIE 4.5 VL 424B-A47B
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-4.5 - Throughput-optimized distillation
GLM · GLM-4.5
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for GLM-4.5 - Quality-retention distillation
GLM · GLM-4.5
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for GLM-4.7 - Throughput-optimized distillation
GLM · GLM-4.7
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for GLM-4.7 - Quality-retention distillation
GLM · GLM-4.7
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for GLM-5.3-Flash - Throughput-optimized distillation
GLM · GLM-5.3-Flash
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
USD 240,363
One-time engineering
Design validated
Production distillation package for GLM-5.3-Flash - Quality-retention distillation
GLM · GLM-5.3-Flash
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
USD 240,363
One-time engineering
Design validated
Production distillation package for MiMo-V2.5 - Throughput-optimized distillation
MiMo · MiMo-V2.5
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for MiMo-V2.5 - Quality-retention distillation
MiMo · MiMo-V2.5
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 240,363
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 300B-A47B - Throughput-optimized distillation
ERNIE · ERNIE 4.5 300B-A47B
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 240,363
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 300B-A47B - Quality-retention distillation
ERNIE · ERNIE 4.5 300B-A47B
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 240,363
One-time engineering
Design validated
Production distillation package for Qwen3 235B-A22B - Throughput-optimized distillation
Qwen · Qwen3 235B-A22B
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Qwen3 235B-A22B - Quality-retention distillation
Qwen · Qwen3 235B-A22B
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Qwen3-VL 235B-A22B Thinking - Throughput-optimized distillation
Qwen · Qwen3-VL 235B-A22B Thinking
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Qwen3-VL 235B-A22B Thinking - Quality-retention distillation
Qwen · Qwen3-VL 235B-A22B Thinking
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Qwen3-VL 235B-A22B Instruct - Throughput-optimized distillation
Qwen · Qwen3-VL 235B-A22B Instruct
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Qwen3-VL 235B-A22B Instruct - Quality-retention distillation
Qwen · Qwen3-VL 235B-A22B Instruct
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Command A+ 05-2026 - Throughput-optimized distillation
Command A · Command A+ 05-2026
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Command A+ 05-2026 - Quality-retention distillation
Command A · Command A+ 05-2026
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Step 3.7 Flash - Throughput-optimized distillation
StepFun · Step 3.7 Flash
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Step 3.7 Flash - Quality-retention distillation
StepFun · Step 3.7 Flash
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Step 3.5 Flash - Throughput-optimized distillation
StepFun · Step 3.5 Flash
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Step 3.5 Flash - Quality-retention distillation
StepFun · Step 3.5 Flash
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
USD 240,363
One-time engineering
Design validated
Production distillation package for Mistral Small 4 119B A6B - 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
USD 150,535
One-time engineering
Design validated
Production distillation package for Mistral Small 4 119B A6B - 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
USD 150,535
One-time engineering
Design validated
Production distillation package for GPT-OSS 120B - Throughput-optimized distillation
GPT-OSS · GPT-OSS 120B
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
USD 150,535
One-time engineering
Design validated
Production distillation package for GPT-OSS 120B - Quality-retention distillation
GPT-OSS · GPT-OSS 120B
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
USD 150,535
One-time engineering
Design validated
Production distillation package for Qwen3 Coder Next - Throughput-optimized distillation
Qwen · Qwen3 Coder Next
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
USD 150,535
One-time engineering
Design validated
Production distillation package for Qwen3 Coder Next - Quality-retention distillation
Qwen · Qwen3 Coder Next
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
USD 150,535
One-time engineering
Design validated
Production distillation package for LongCat Flash Lite Sparse - Throughput-optimized distillation
LongCat · LongCat Flash Lite Sparse
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 99,205
One-time engineering
Design validated
Production distillation package for LongCat Flash Lite Sparse - Quality-retention distillation
LongCat · LongCat Flash Lite Sparse
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 99,205
One-time engineering
Design validated
Production distillation package for Seed-OSS 36B Instruct - Throughput-optimized distillation
Seed-OSS · Seed-OSS 36B Instruct
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
USD 70,000
One-time engineering
Design validated
Production distillation package for Seed-OSS 36B Instruct - Quality-retention distillation
Seed-OSS · Seed-OSS 36B Instruct
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
USD 70,000
One-time engineering
Design validated
Production distillation package for Yi 1.5 34B - Throughput-optimized distillation
Yi · Yi 1.5 34B
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
USD 70,000
One-time engineering
Design validated
Production distillation package for Yi 1.5 34B - Quality-retention distillation
Yi · Yi 1.5 34B
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
USD 70,000
One-time engineering
Design validated
Production distillation package for Step-Audio R1.1 - Throughput-optimized distillation
StepFun · Step-Audio R1.1
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
USD 70,000
One-time engineering
Design validated
Production distillation package for Step-Audio R1.1 - Quality-retention distillation
StepFun · Step-Audio R1.1
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
USD 70,000
One-time engineering
Design validated
Production distillation package for OLMo 3.1 32B Instruct - Throughput-optimized distillation
OLMo · OLMo 3.1 32B Instruct
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
USD 70,000
One-time engineering
Design validated
Production distillation package for OLMo 3.1 32B Instruct - Quality-retention distillation
OLMo · OLMo 3.1 32B Instruct
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
USD 70,000
One-time engineering
Design validated
Production distillation package for OLMo 2 32B - Throughput-optimized distillation
OLMo · OLMo 2 32B
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
USD 47,875
One-time engineering
Design validated
Production distillation package for OLMo 2 32B - Quality-retention distillation
OLMo · OLMo 2 32B
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Qwen3-VL 32B Thinking - Throughput-optimized distillation
Qwen · Qwen3-VL 32B Thinking
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Qwen3-VL 32B Thinking - Quality-retention distillation
Qwen · Qwen3-VL 32B Thinking
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Qwen3-VL 32B Instruct - Throughput-optimized distillation
Qwen · Qwen3-VL 32B Instruct
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Qwen3-VL 32B Instruct - Quality-retention distillation
Qwen · Qwen3-VL 32B Instruct
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Gemma 4 31B IT - Throughput-optimized distillation
Gemma · Gemma 4 31B IT
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Gemma 4 31B IT - Quality-retention distillation
Gemma · Gemma 4 31B IT
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Granite 4.2 30B - Throughput-optimized distillation
IBM Granite · Granite 4.2 30B
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, 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 47,875
One-time engineering
Design validated
Production distillation package for Granite 4.2 30B - Quality-retention distillation
IBM Granite · Granite 4.2 30B
Package profile: Quality-retention distillation
Transformation operations: Distillation, 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 47,875
One-time engineering
Design validated
Production distillation package for Granite 4.1 30B - Throughput-optimized distillation
IBM Granite · Granite 4.1 30B
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Granite 4.1 30B - Quality-retention distillation
IBM Granite · Granite 4.1 30B
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
USD 47,875
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 VL 28B-A3B Thinking - Throughput-optimized distillation
ERNIE · ERNIE 4.5 VL 28B-A3B Thinking
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 VL 28B-A3B Thinking - Quality-retention distillation
ERNIE · ERNIE 4.5 VL 28B-A3B Thinking
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for Wan2.2 I2V A14B - Throughput-optimized distillation
Wan · Wan2.2 I2V A14B
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for Wan2.2 I2V A14B - Quality-retention distillation
Wan · Wan2.2 I2V A14B
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for Wan2.2 T2V A14B - Throughput-optimized distillation
Wan · Wan2.2 T2V A14B
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for Wan2.2 T2V A14B - Quality-retention distillation
Wan · Wan2.2 T2V A14B
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for Gemma 4 26B-A4B IT - Throughput-optimized distillation
Gemma · Gemma 4 26B-A4B IT
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
USD 67,124
One-time engineering
Design validated
Production distillation package for Gemma 4 26B-A4B IT - Quality-retention distillation
Gemma · Gemma 4 26B-A4B IT
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
USD 67,124
One-time engineering
Design validated
Production distillation package for Devstral Small 2 24B - Throughput-optimized distillation
Mistral · Devstral Small 2 24B
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
USD 47,875
One-time engineering
Design validated
Production distillation package for Devstral Small 2 24B - Quality-retention distillation
Mistral · Devstral Small 2 24B
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
USD 47,875
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 21B-A3B Thinking - Throughput-optimized distillation
ERNIE · ERNIE 4.5 21B-A3B Thinking
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 21B-A3B Thinking - Quality-retention distillation
ERNIE · ERNIE 4.5 21B-A3B Thinking
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 21B-A3B - Throughput-optimized distillation
ERNIE · ERNIE 4.5 21B-A3B
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for ERNIE 4.5 21B-A3B - Quality-retention distillation
ERNIE · ERNIE 4.5 21B-A3B
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: fastdeploy
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 67,124
One-time engineering
Design validated
Production distillation package for GPT-OSS 20B - Throughput-optimized distillation
GPT-OSS · GPT-OSS 20B
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
USD 67,124
One-time engineering
Design validated
Production distillation package for GPT-OSS 20B - Quality-retention distillation
GPT-OSS · GPT-OSS 20B
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
USD 67,124
One-time engineering
Design validated
Production distillation package for Qwen Image - Throughput-optimized distillation
Qwen Image · Qwen Image
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 47,875
One-time engineering
Design validated
Production distillation package for Qwen Image - Quality-retention distillation
Qwen Image · Qwen Image
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 47,875
One-time engineering
Design validated
Production distillation package for Qwen Image Layered - Throughput-optimized distillation
Qwen Image · Qwen Image Layered
Package profile: Throughput-optimized distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 47,875
One-time engineering
Design validated
Production distillation package for Qwen Image Layered - Quality-retention distillation
Qwen Image · Qwen Image Layered
Package profile: Quality-retention distillation
Transformation operations: Distillation, Evaluation and benchmarking
Target GPU: Hardware selected in the builder
Runtime packaging: diffusers
Configured delivery: Download package
Delivery options: Download package / Host with FusionPointAI / Download + host
USD 47,875
One-time engineering