Mistral-Small-4-119B-2603
mistralai/Mistral-Small-4-119B-2603
Official · FP8 · safetensors
Runtime certified: Transformers vLLM SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| FP8 | safetensors | 8 | Official | Runtime certified |
Mistral · Generalist Small · Mistral Small 4
Mistral Small 4 119B A6B: Specs, GPU requirements, hosting & deployment
Mistral Small 4 119B A6B is a current Generalist Small release in the Mistral family, certified from its immutable official source revision.
Total parameters119.0B
Active parameters6.0B
Context window1,048,576 tokens
Release statusCurrent · Current
ArchitectureMistral3ForConditionalGeneration
ModalitiesText
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2026-01-23
Architecture, strengths and use cases
Mistral Small 4 119B A6B is an official self-hostable Mistral AI release in the Mistral Generalist Small track. It uses Mistral3ForConditionalGeneration, carries 119B / 6B MoE, supports a verified context window of 1,048,576 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Mistral Small 4 119B A6B uses Mistral3ForConditionalGeneration with 119B / 6B MoE. The stored architecture profile records 36 layers, hidden width 4096, 32 attention heads and a 1,048,576 token context ceiling where the official configuration publishes those fields.
Verified Mistral3ForConditionalGeneration architecture
1,048,576 token certified context
Official FP8, NVFP4 checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Mistral-Small-4-119B-2603-NVFP4
mistralai/Mistral-Small-4-119B-2603-NVFP4
Official · NVFP4 · safetensors
Runtime certified: Transformers vLLM SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| NVFP4 | safetensors | 4 | Official | Runtime certified |
Recommended hardware
Use only the listed transformers, vllm, sglang runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory114.15 GB
KV cache2.25 GB
Runtime overhead37.8 GB
Total with safety margin191.21 GB
Recommended best value
3× NVIDIA H100 SXM 80GB
240 GB total VRAM · nvswitch
48.79 GB headroom · Available
USD 5,580 / monthLowest-cost viable
2× NVIDIA H200 SXM 141GB
282 GB total VRAM · nvswitch
90.79 GB headroom · Limited capacity
USD 4,690 / monthHighest performance
2× NVIDIA H200 SXM 141GB
282 GB total VRAM · nvswitch
90.79 GB headroom · Limited capacity
USD 4,690 / monthLicense and self-hosting considerations
The full 119B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Mistral Small 4 119B A6B is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Release timeline
mistral-ai/mistral/mistral-small-4-119b @ 37909a0153738d7a6b9e5172ae822191318b7a5f040a84c8346965a01c32d5c4
Frequently asked questions
How much VRAM does Mistral Small 4 119B A6B require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support Mistral Small 4 119B A6B?
Certified upstream runtime evidence is available for transformers, vllm, sglang.
Can Mistral Small 4 119B A6B be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26