Edge

No open-weight 3B Ministral checkpoint is published under this name, so no weights license applies — Mistral's later Ministral 3 3B (2512) is Apache 2.0Open weights where releasedUpdated August 2026

Ministral 3B

Ministral 3B is a Mistral-family model worth evaluating for low-resource local workflows.

Mistral AI · Mistral

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedAugust 2026SourcesOfficial model cards, source links, and OpenSourcesAI editorial review for Ministral 3B.

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

Low-resource local workflows

Who should use it

  • Low-resource local workflows
  • Builders who want local or self-hosted testing options.

Common workflows

  • Low-resource local workflows
  • edge 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

No open-weight 3B Ministral checkpoint is published under this name, so no weights license applies — Mistral's later Ministral 3 3B (2512) is Apache 2.0. 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.
  • Low-resource local workflows
  • 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: Check official model card.
  • 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

Related resources

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

Mistral family hubAI tools directoryModel source notesModels directoryGuides library
HardwareNo open-weight 3B Ministral checkpoint is published on Hugging Face under this name — verify the current Ministral release before planning hardwareRuntimeOllama or LM Studio where supported, llama.cpp, Transformers, vLLMContextCheck official model cardLast updated2026

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

Check if this model fits your GPU →What is quantization? GGUF, Q4, Q8 explained →What is VRAM and how much do you need? →

Related model pages

Mistral family hub →Ministral 8B →Mistral 7B Instruct →Mistral 8x22B Instruct →Codestral 22B →Devstral →Gemma 2 2B Instruct →

Guides, stacks, and comparisons

All model comparisons →

Related models

Ministral 8BEfficient local workflowsMistral 7B InstructLocal assistant baseline workflowsMistral 8x22B InstructMoE assistant evaluationCodestral 22BCoding assistant workflowsDevstralDeveloper and coding workflow evaluationGemma 2 2B InstructEfficient local prototypes, app workflows, and Gemma-family comparisons.

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →