mistralai · fine-tune of mistralai/Mistral-Small-3.1-24B-Base-2503
Devstral-Small-2-24B-Instruct-2512
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.3 GB, worked out from the model's config (mistralai/Devstral-Small-2-24B-Instruct-2512), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
weights context cache runtime
GGUF for llama.cpp, Ollama, LM Studio and others
unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF (converted by unsloth), 153k downloads. Sizes are the real files on the Hub, all parts added up. Showing the common levels.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q4_K_M | 13.3 GBfile size | 15.1 GB13.3 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_MOllama ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_MDownload hf download unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF --include "Devstral-Small-2-24B-Instruct-2512-Q4_K_M.gguf" --local-dir Devstral-Small-2-24B-Instruct-2512-GGUF | |
| Q5_K_M | 15.6 GBfile size | 17.4 GB15.6 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q5_K_MOllama ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q5_K_MDownload hf download unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF --include "Devstral-Small-2-24B-Instruct-2512-Q5_K_M.gguf" --local-dir Devstral-Small-2-24B-Instruct-2512-GGUF | |
| Q6_K | 18.0 GBfile size | 19.8 GB18.0 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q6_KOllama ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q6_KDownload hf download unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF --include "Devstral-Small-2-24B-Instruct-2512-Q6_K.gguf" --local-dir Devstral-Small-2-24B-Instruct-2512-GGUF | |
| Q8_0 | 23.3 GBfile size | 25.1 GB23.3 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q8_0Ollama ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q8_0Download hf download unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF --include "Devstral-Small-2-24B-Instruct-2512-Q8_0.gguf" --local-dir Devstral-Small-2-24B-Instruct-2512-GGUF | |
| BF16 | 43.9 GBfile size | 45.7 GB43.9 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:BF16Ollama ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:BF16Download hf download unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF --include "Devstral-Small-2-24B-Instruct-2512-BF16.gguf" --local-dir Devstral-Small-2-24B-Instruct-2512-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX 4bitmlx-community/Devstral-Small-2-24B-Instruct-2512-4bit | 14.1 GBfile size | 15.8 GB14.1 + 1.3 + 0.50 | Download page | |
| MLX 8bitmlx-community/mistralai_Devstral-Small-2-24B-Instruct-2512-MLX-8Bit | 24.7 GBfile size | 26.5 GB24.7 + 1.3 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| F8_E4M3original weights | 24.0 GBfile size | 25.8 GB24.0 + 1.3 + 0.50 |
hf download mistralai/Devstral-Small-2-24B-Instruct-2512 --local-dir Devstral-Small-2-24B-Instruct-2512Other conversions (6; sizes not read)
- cyankiwi/Devstral-Small-2-24B-Instruct-2512-AWQ-4bit AWQ, 4bit, 1.9k downloads
- unsloth/Devstral-Small-2-24B-Instruct-2512 FP8, 1.1k downloads
- Firworks/Devstral-Small-2-24B-Instruct-2512-nvfp4 NVFP4, 225 downloads
- gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8 FP8, 140 downloads
- androiddrew/Devstral-Small-2-24B-Instruct-2512-AWQ-4bit AWQ, 4bit, 54 downloads
- DeathGodlike/Devstral-Small-2-24B-Instruct-2512_EXL3 EXL3, 13 downloads
The Hub tags 47 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 15:16 UTC. The repo. Found a mistake on this page? Tell us.