community pool / model answer
Mistral-Small-3.2-24B-Instruct-2506
chat · mistralai/Mistral-Small-3.2-24B-Instruct-2506
39.4 tok/s · model median · 3 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| M1 Max 64GB | 4-bit | 11.2 tok/s | reported | 88 | - GB | 2,048 | ollama |
| M3 Ultra 512GB | 4-bit | 39.5 tok/s | reported | 129 | - GB | 8,192 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.