Code

Apache 2.0Open weights where releasedUpdated October 2026

Devstral

Devstral is a Mistral-family model worth evaluating for developer and coding workflow evaluation.

Mistral AI · Mistral

Editorial details

EditorCJ ZwartLast updatedOctober 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

Developer and coding workflow evaluation

Who should use it

  • Developer and coding workflow evaluation
  • Builders who want local or self-hosted testing options.

Common workflows

  • Developer and coding workflow evaluation
  • code 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

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.
  • Developer and coding workflow 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 Devstral run on your machine?

Devstral is 23.6B parameters and needs 15.8 GB of VRAM at Q4_K_M: 14.3 GB of weights plus 1.5 GB of runtime overhead for the inference server itself.

VRAM by quantization

QuantizationWeightsNeeds (with overhead)Quality
Q4_K_M14.3 GB15.8 GBgood
Q8_025 GB26.5 GBhigh
FP1647 GB48.5 GBreference

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 GBCPU offload
RTX 4060 Ti (16GB)16 GB32 GBTight
RTX 309024 GB64 GBComfortable
Apple Silicon (Unified Memory) 36 GB24 GB of 36 GB36 GBComfortable
RTX 509032 GB64 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 usable share the Compatibility Checker uses (two-thirds of the pool on Macs up to 36 GB, three-quarters above), which is why a 36 GB Mac is graded on 24 GB.

Check Devstral against your exact hardwareHow these verdicts are calculated

Want a broader hardware plan around Devstral? Open the PC Builder for the whole 30B / 32B class → The Builder plans across that class; it does not replace the exact-model fit verdict above.

VRAM fit by quantization level

Enter your GPU VRAM below to see which quantization of Devstral 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.

Open-source AI coding assistantsLocal coding assistant stackCursor vs Devin Desktop vs ClineAI tools directoryModel source notes
Hardware~14.3 GB at Q4_K_M (23.6B parameters)RuntimeOllama or LM Studio where supported, llama.cpp, Transformers, vLLMContext131,072 tokensLast updatedOctober 2026
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

Check if this model fits your GPU →What can 16GB VRAM run? →What is quantization? GGUF, Q4, Q8 explained →What is VRAM and how much do you need? →

Related model pages

Mathstral 7B →Ministral 8B →Mistral 7B Instruct →Qwen2.5 Coder 14B →Qwen2.5 Coder 32B →CodeGemma 7B →

Guides, stacks, and comparisons

Open-source AI coding assistants →Local coding assistant stack →Cursor vs Devin Desktop vs Cline →All model comparisons →

Related models

Mathstral 7BMath and reasoning evaluationMinistral 8BEfficient local workflowsMistral 7B InstructLocal assistant baseline workflowsQwen2.5 Coder 14BCoding assistants, repository help, and developer workflow evaluation.Qwen2.5 Coder 32BCoding assistants, repository help, and developer workflow evaluation.CodeGemma 7BCoding assistant experiments and developer workflow prototypes.

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →