Chat

Mistral Research License (non-commercial)Open weights where releasedUpdated August 2026

Mistral Large 2

Mistral Large 2 is a Mistral-family model worth evaluating for large multilingual assistant evaluation.

Mistral AI · Mistral

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedAugust 2026SourcesExact model card

Model checkpoints, context windows, provider support, local runtime compatibility, and license terms can change quickly. Verify the exact model card before production or commercial use.

Best for

Large multilingual assistant evaluation

Who should use it

  • Large multilingual assistant evaluation
  • Builders who want local or self-hosted testing options.

Common workflows

  • Large multilingual assistant evaluation
  • chat workflows
  • local workflows
  • open weights workflows

Deployment and hardware notes

Local hardware needs vary by size, quantization, and runtime. Check the exact model card and serving stack.

License and usage notes

Mistral Research License (non-commercial). Open weights where released. Verify the exact model card and license terms for the checkpoint or hosted provider you use.

Strengths

  • Open weights where released model option for Mistral workflows.
  • Large multilingual assistant evaluation
  • Use the exact checkpoint and quantization that matches your hardware and latency target.

Limitations

  • Verify license, deployment requirements, runtime support, and fit on your own workload before production use.
  • Local hardware needs vary by size, quantization, and runtime. Check the exact model card and serving stack.
  • Context window and limits: 131,072 tokens.
  • Verify the exact model card, provider docs, license, and serving support before production use.

Local workflow notes

Use the exact checkpoint and quantization that matches your hardware and latency target.

Local runtimes: Ollama where supported, LM Studio where supported, llama.cpp where supported, Transformers

Platforms: Windows, macOS, Linux

Will Mistral Large 2 run on your machine?

Mistral Large 2 is 123B parameters and needs 76.5 GB of VRAM at Q4_K_M — 75 GB of weights plus 1.5 GB of runtime overhead for the inference server itself.

VRAM by quantization

QuantizationWeightsNeeds (with overhead)Quality
Q4_K_M75 GB76.5 GBgood
Q8_0131 GB132.5 GBhigh

Fit on common hardware at Q4_K_M

HardwareMemory the model can useSystem RAMVerdict
CPU OnlyNone (CPU only)16 GBToo large
RTX 4060 Laptop8 GB16 GBToo large
RTX 3060 (12GB)12 GB32 GBToo large
RTX 4060 Ti (16GB)16 GB32 GBToo large
RTX 309024 GB64 GBToo large
Apple Silicon (Unified Memory) 36 GB27 GB of 36 GB36 GBToo large
RTX 509032 GB64 GBToo large
Apple Silicon (Unified Memory) 48 GB36 GB of 48 GB48 GBToo large
Apple Silicon (Unified Memory) 64 GB48 GB of 64 GB64 GBToo large
Apple Silicon (Unified Memory) 96 GB72 GB of 96 GB96 GBToo large
Apple Silicon (Unified Memory) 128 GB96 GB of 128 GB128 GBComfortable
Apple Silicon (Unified Memory) 192 GB144 GB of 192 GB192 GBComfortable

Comfortable means VRAM clears the requirement by 2 GB or more. Tight means it covers the requirement with no margin. CPU offload means the model does not fit in VRAM but system RAM is at least 1.6× the weights, so it will run at reduced speed — expect roughly 1–5 tokens per second. Figures are weights plus a fixed runtime overhead and exclude KV-cache growth, which scales with context length.

Apple Silicon shares one pool of memory between the system and the GPU, so a model cannot use all of it. These rows apply the same 75% usable fraction the Compatibility Checker uses, which is why a 36 GB Mac is graded on less than 36 GB.

Check Mistral Large 2 against your exact hardwareHow these verdicts are calculated

Need more hardware for Mistral Large 2? Open the PC Builder for the MoE / frontier-style experiment tier →

VRAM fit by quantization level

Enter your GPU VRAM below to see which quantization of Mistral Large 2 fits and get the Ollama run command.

Sources to verify

Exact model card

Related resources

Continue with model source notes, local tools, and implementation guides related to this model.

Mistral family hubBest local LLM toolsPrivate local chatbot stackOllama + Open WebUI starter stackAI tools directory
Hardware~74.3 GB at Q4_K_M (122.6B parameters) — multi-GPU or server classRuntimeOllama or LM Studio where supported, llama.cpp, Transformers, vLLMContext131,072 tokensLast updated2026
Exact model card →

Model ecosystem connections

Use these next-step links to move from this profile into related tools, comparisons, guides, stacks, and curated shortlists.

Recommended runtimes and tools

Ollama →LM Studio →llama.cpp →Transformers →vLLM →

Setup and deployment

What is quantization? GGUF, Q4, Q8 explained →RunPod — managed GPU cloud →Lambda Labs — A100 / H100 on demand →Vast.ai — crowdsourced GPU marketplace →

Related model pages

Mistral family hub →Mistral Small 3.1 →Mixtral 8x7B Instruct →Pixtral 12B →Codestral 22B →DeepSeek V3 →Devstral →

Guides, stacks, and comparisons

Best local LLM tools →Private local chatbot stack →Ollama + Open WebUI starter stack →All model comparisons →

Related models

Mistral Small 3.1Builders who want a smaller capable model with permissive licensing and good local runtime support.Mixtral 8x7B InstructMoE local and hosted baseline workflowsPixtral 12BVision-language local and hosted experimentsCodestral 22BCoding assistant workflowsDeepSeek V3General DeepSeek-family comparisons and assistant workflow evaluation.DevstralDeveloper and coding workflow evaluation

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →