community pool / model answer
Qwen3.8-27B-GGUF
chat · ggml-org/Qwen3.8-27B-GGUF
44.6 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B70 32GB | 4-bit | 27.8 tok/s | reported | 255 | - GB | 8,192 | llama.cpp |
| Arc Pro B70 32GB ×2 | 4-bit | 45.9 tok/s | measured | 174 | - 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.