mistralai · fine-tune of mistralai/Mistral-Small-24B-Base-2501
Mistral-Small-24B-Instruct-2501
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-24B-Instruct-2501), 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
MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF (converted by MaziyarPanahi), 41k 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 MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q4_K_MOllama ollama run hf.co/MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q4_K_MDownload hf download MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF --include "Mistral-Small-24B-Instruct-2501.Q4_K_M.gguf" --local-dir Mistral-Small-24B-Instruct-2501-GGUF | |
| Q5_K_M | 15.6 GBfile size | 17.4 GB15.6 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q5_K_MOllama ollama run hf.co/MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q5_K_MDownload hf download MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF --include "Mistral-Small-24B-Instruct-2501.Q5_K_M.gguf" --local-dir Mistral-Small-24B-Instruct-2501-GGUF | |
| Q6_K | 18.0 GBfile size | 19.8 GB18.0 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q6_KOllama ollama run hf.co/MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q6_KDownload hf download MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF --include "Mistral-Small-24B-Instruct-2501.Q6_K.gguf" --local-dir Mistral-Small-24B-Instruct-2501-GGUF | |
| Q8_0 | 23.3 GBfile size | 25.1 GB23.3 + 1.3 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q8_0Ollama ollama run hf.co/MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF:Q8_0Download hf download MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF --include "Mistral-Small-24B-Instruct-2501.Q8_0.gguf" --local-dir Mistral-Small-24B-Instruct-2501-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX 4bitmlx-community/Mistral-Small-24B-Instruct-2501-4bit | 12.3 GBfile size | 14.1 GB12.3 + 1.3 + 0.50 | Download page | |
| MLX 8bitmlx-community/Mistral-Small-24B-Instruct-2501-8bit | 23.3 GBfile size | 25.1 GB23.3 + 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 | 43.9 GBfile size | 45.7 GB43.9 + 1.3 + 0.50 |
hf download mistralai/Mistral-Small-24B-Instruct-2501 --local-dir Mistral-Small-24B-Instruct-2501Other conversions (21; sizes not read)
- RedHatAI/Mistral-Small-24B-Instruct-2501-FP8-dynamic FP8, 90k downloads
- stelterlab/Mistral-Small-24B-Instruct-2501-AWQ AWQ, 22k downloads
- RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8 Other, w8a8, 14k downloads
- unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit bitsandbytes, 4bit, 6.5k downloads
- unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit bitsandbytes, 4bit, 1.3k downloads
- RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w4a16 Other, w4a16, 219 downloads
- cortecs/Mistral-Small-24B-Instruct-2501-FP8-Dynamic FP8, 65 downloads
- dark-side-of-the-code/Mistral-Small-24B-Instruct-2501-AWQ AWQ, 34 downloads
- llmat/Mistral-Small-24B-Instruct-2501-NVFP4 NVFP4, 25 downloads
- starsy/Mistral-Small-24B-Instruct-2501-FP8-Dynamic FP8, 19 downloads
- noneUsername/Mistral-Small-24B-Instruct-2501-W8A8 Other, w8a8, 15 downloads
- EliasOenal/Mistral-Small-24B-Instruct-2501-W8A8-dynamic Other, w8a8, 13 downloads
- fbaldassarri/mistralai_Mistral-Small-24B-Instruct-2501-autoround-int4-gs128-asym GPTQ, int4, 13 downloads
- fbaldassarri/mistralai_Mistral-Small-24B-Instruct-2501-autoround-int8-gs128-asym GPTQ, int8, 13 downloads
- fbaldassarri/mistralai_Mistral-Small-24B-Instruct-2501-autoround-int4-gs128-sym GPTQ, int4, 12 downloads
- fbaldassarri/mistralai_Mistral-Small-24B-Instruct-2501-autoround-int8-gs128-sym GPTQ, int8, 12 downloads
- minicreeper/Mistral-Small-24B-Instruct-2501-bnb-4bit bitsandbytes, 4bit, 10 downloads
- Jellon/Mistral-Small-24B-Instruct-2501-exl2-4bpw EXL2, 8 downloads
- Jellon/Mistral-Small-24B-Instruct-2501-exl2-6bpw EXL2, 6 downloads
- DeusImperator/Mistral-Small-24B-Instruct-2501_exl2_6.5bpw_L EXL2, 6 downloads
- altomek/Mistral-Small-24B-Instruct-2501-8bpw-EXL2 EXL2, 3 downloads
The Hub tags 100 or more 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
- unsloth/Mistral-Small-24B-Instruct-250123.6B38kUnreviewed
- dphn/Dolphin-Mistral-24B-Venice-Edition24.0B6.6kUnreviewed
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.