community pool / model answer
North-Mini-Code-1.0
code · CohereLabs/North-Mini-Code-1.0
101.6 tok/s · model median · 17 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 4-bit | 89.5 tok/s | measured | 2,033 | 19.6 GB | 32,768 | llama.cpp |
| RTX 3090 24GB | 4-bit | 151.5 tok/s | measured | - | - GB | 131,072 | llama.cpp |
| RTX 5090 32GB | 6-bit | 258.4 tok/s | reported | 49 | 26.9 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.