community pool / model answer
Qwen3.5-4B-q8_0-am17an-MTP
chat · adriabama06/Qwen3.5-4B-q8_0-am17an-MTP
52.4 tok/s · model median · 1 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 8-bit | 52.4 tok/s | reported | - | 8.9 GB | 128,000 | 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.