community pool / model answer
Qwen3-VL-8B-Instruct
chat · Qwen/Qwen3-VL-8B-Instruct
89.8 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Radeon AI Pro R9700 32GB ×3 | 8-bit | 58.8 tok/s | reported | 174 | 15.5 GB | 786 | llama.cpp |
| RX 7900 XTX 24GB | 8-bit | 89.8 tok/s | reported | 201 | - 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.