community pool / model answer
Carnice-9b-GGUF
chat · kai-os/Carnice-9b-GGUF
51.7 tok/s · model median · 19 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 4-bit | 52 tok/s | measured | 2,108 | 7.3 GB | 131,072 | llama.cpp |
| RTX 3060 12GB ×2 | 4-bit | 51.6 tok/s | measured | 5,646 | 7.2 GB | 131,072 | 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.