mradermacher / mistral family
pixtral-large
mistral/pixtral-large
Run locally Smallest indexed GGUF / needs Ollama
ollama run hf.co/mistral/pixtral-large/Pixtral-Large-Instruct-124B-2411-GH2TS-Q2_K.gguf Benchmarks
Where it scores.
General Provisional
64.0
Coding Provisional —
Math Provisional —
Reasoning Provisional —
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| Q2_K / smallest | GGUF | 46.7 GB | — | Pixtral-Large-Instruct-124B-2411-GH2TS-Q2_K.gguf |
| Q2_K_L | GGUF | 58.6 GB | — | Pixtral-Large-Instruct-124B-2411-GH2TX-Q2_K_L.gguf |
| Q3_K_L | GGUF | 66.6 GB | — | Pixtral-Large-Instruct-124B-2411-GH3TX-Q3_K_L.gguf |
| Q4_K_XL | GGUF | 77.4 GB | — | Pixtral-Large-Instruct-124B-2411-GH4TX-Q4_K_XL.gguf |
| Q5_K_XL | GGUF | 96.1 GB | — | Pixtral-Large-Instruct-124B-2411-GH5TX-Q5_K_XL.gguf |
| Q6_K_L | GGUF | 111.9 GB | — | Pixtral-Large-Instruct-124B-2411-GH6TX-Q6_K_L.gguf |
Sizes are file sizes, not peak runtime memory.
Raw benchmarks
The inputs.
| Source | Task | Raw | Normalized |
|---|---|---|---|
| ZeroEval | MMMU | 64.0 | 64.0 |
From the Hugging Face model card
About this model.
From the Hugging Face model card