mistralai · fine-tune of mistralai/Mistral-Small-3.1-24B-Base-2503
Mistral-Small-3.2-24B-Instruct-2506
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/Mistral-Small-3.2-24B-Instruct-2506), 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/Mistral-Small-3.2-24B-Instruct-2506-GGUF (converted by unsloth), 134k 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/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_MOllama ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_MDownload hf download unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF --include "Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf" --local-dir Mistral-Small-3.2-24B-Instruct-2506-GGUF | |
| Q5_K_M | 15.6 GBfile size | 17.4 GB15.6 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q5_K_MOllama ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q5_K_MDownload hf download unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF --include "Mistral-Small-3.2-24B-Instruct-2506-Q5_K_M.gguf" --local-dir Mistral-Small-3.2-24B-Instruct-2506-GGUF | |
| Q6_K | 18.0 GBfile size | 19.8 GB18.0 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q6_KOllama ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q6_KDownload hf download unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF --include "Mistral-Small-3.2-24B-Instruct-2506-Q6_K.gguf" --local-dir Mistral-Small-3.2-24B-Instruct-2506-GGUF | |
| Q8_0 | 23.3 GBfile size | 25.1 GB23.3 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q8_0Ollama ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q8_0Download hf download unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF --include "Mistral-Small-3.2-24B-Instruct-2506-Q8_0.gguf" --local-dir Mistral-Small-3.2-24B-Instruct-2506-GGUF | |
| BF16 | 43.9 GBfile size | 45.7 GB43.9 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:BF16Ollama ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:BF16Download hf download unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF --include "Mistral-Small-3.2-24B-Instruct-2506-BF16.gguf" --local-dir Mistral-Small-3.2-24B-Instruct-2506-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX 6bitlmstudio-community/Mistral-Small-3.2-24B-Instruct-2506-MLX-6bit | 18.6 GBfile size | 20.4 GB18.6 + 1.3 + 0.50 | Download page | |
| MLX 8bitlmstudio-community/Mistral-Small-3.2-24B-Instruct-2506-MLX-8bit | 24.1 GBfile size | 25.9 GB24.1 + 1.3 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 44.7 GBfile size | 46.5 GB44.7 + 1.3 + 0.50 |
hf download mistralai/Mistral-Small-3.2-24B-Instruct-2506 --local-dir Mistral-Small-3.2-24B-Instruct-2506Other conversions (14; sizes not read)
- jeffcookio/Mistral-Small-3.2-24B-Instruct-2506-awq-sym AWQ, 3.8k downloads
- unsloth/Mistral-Small-3.2-24B-Instruct-2506-bnb-4bit bitsandbytes, 4bit, 3.7k downloads
- unsloth/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit bitsandbytes, 4bit, 1.8k downloads
- stelterlab/Mistral-Small-3.2-24B-Instruct-2506-FP8 FP8, 1.4k downloads
- Intel/Mistral-Small-3.2-24B-Instruct-2506-int4-AutoRound Other, int4, 998 downloads
- gratex/Mistral-Small-3.2-24B-Instruct-2506-W4A16-AutoRound Other, w4a16, 380 downloads
- gratex/mistral-small-3.2-24b-Instruct-2506-NVFP4A16 NVFP4, 195 downloads
- ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3 EXL3, 51 downloads
- mmr94000/Mistral-Small-3.2-24B-Instruct-2506-awq-sym AWQ, 17 downloads
- cronopioelectronico/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit bitsandbytes, 4bit, 16 downloads
- Jellon/Mistral-Small-3.2-24B-Instruct-2506-exl3-6bpw EXL3, 14 downloads
- async0x42/Mistral-Small-3.2-24B-Instruct-2506-exl3_4.0bpw EXL3, 11 downloads
- Jellon/Mistral-Small-3.2-24B-Instruct-2506-exl3-4bpw EXL3, 10 downloads
- VAmblardPEReN/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GPTQ GPTQ, 0 downloads
The Hub tags 72 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.
Fine-tunes of this model
- mistralai/Magistral-Small-250924.0B15kUnreviewed
- lmstudio-community/Mistral-Small-3.2-24B-Instruct-2506-MLX-4bit15kUnreviewed
- unsloth/Mistral-Small-3.2-24B-Instruct-250624.0B7.2kUnreviewed
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.