Skip to main content

Mistral / Mistral Large 3 675B Instruct 2512

Transformation options for Mistral Large 3 675B Instruct 2512

Validated per release from registry evidence, pricing components and runtime compatibility.

Technical transformation state

Transformation supported

Verified public open-weight release with authoritative checkpoint evidence.

Architecture

MistralLarge3ForConditionalGeneration

Parameters: 675.00B · Context window: 294,912

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 package

Validated per release

Published packages

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

fp8vllm Download packageHost with FusionPointAIDownload + 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

fp8GPU targeted7 × NVIDIA H200 SXM 141GBvllmRuntime optimized Download packageHost with FusionPointAIDownload + host

USD 112,700
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

DistillationQuality retentionvllm Download packageHost with FusionPointAIDownload + 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

DistillationThroughput optimizedvllm Download packageHost with FusionPointAIDownload + host

USD 240,363
One-time engineering