community pool / model answer
Qwen3Guard-Gen-4B
chat · Qwen/Qwen3Guard-Gen-4B
66.8 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RX 9060 XT 16GB | 8-bit | 66.8 tok/s | reported | 2,264 | 5.5 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.