community pool / model answer
Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced
chat · HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced
31.6 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 4-bit | 38.4 tok/s | reported | 3,331 | 9.9 GB | 4,608 | llama.cpp |
| Ryzen AI Max 395 128GB | 4-bit | 24.8 tok/s | reported | 216 | 9.7 GB | 4,096 | 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.