MaziyarPanahi / mistral family / text-generation
mistral-small-2409
mistral/mistral-small-2409
Run locally Smallest indexed GGUF / needs Ollama
ollama run hf.co/mistral/mistral-small-2409/Mistral-Small-Instruct-2409.IQ1_S.gguf Benchmarks
Where it scores.
General Provisional —
Coding Provisional —
Math Provisional —
Reasoning Provisional —
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| Q4 / smallest | GGUF | 4.8 GB | — | Mistral-Small-Instruct-2409.IQ1_S.gguf |
| Q4 | GGUF | 5.3 GB | — | Mistral-Small-Instruct-2409.IQ1_M.gguf |
| Q4 | GGUF | 6.6 GB | — | Mistral-Small-Instruct-2409.IQ2_XS.gguf |
| Q2_K | GGUF | 8.3 GB | — | Mistral-Small-Instruct-2409.Q2_K.gguf |
| Q4 | GGUF | 9.2 GB | — | Mistral-Small-Instruct-2409.IQ3_XS.gguf |
| Q3_K_S | GGUF | 9.6 GB | — | Mistral-Small-Instruct-2409.Q3_K_S.gguf |
| Q3_K_M | GGUF | 10.8 GB | — | Mistral-Small-Instruct-2409.Q3_K_M.gguf |
| Q3_K_L | GGUF | 11.7 GB | — | Mistral-Small-Instruct-2409.Q3_K_L.gguf |
| Q4 | GGUF | 11.9 GB | — | Mistral-Small-Instruct-2409.IQ4_XS.gguf |
| Q4_K_S | GGUF | 12.7 GB | — | Mistral-Small-Instruct-2409.Q4_K_S.gguf |
| Q4_K_M | GGUF | 13.3 GB | — | Mistral-Small-Instruct-2409.Q4_K_M.gguf |
| Q5_K_S | GGUF | 15.3 GB | — | Mistral-Small-Instruct-2409.Q5_K_S.gguf |
| Q5_K_M | GGUF | 15.7 GB | — | Mistral-Small-Instruct-2409.Q5_K_M.gguf |
| Q6_K | GGUF | 18.3 GB | — | Mistral-Small-Instruct-2409.Q6_K.gguf |
| Q8_0 | GGUF | 23.6 GB | — | Mistral-Small-Instruct-2409.Q8_0.gguf |
| Q4 | GGUF | 44.5 GB | — | Mistral-Small-Instruct-2409.fp16.gguf |
Sizes are file sizes, not peak runtime memory.
From the Hugging Face model card
About this model.
From the Hugging Face model card