community pool / model answer
QUEST-30B-RL-B70-Turbo-GGUF
chat · Frosty40/QUEST-30B-RL-B70-Turbo-GGUF
77.2 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B60 24GB | 5-bit | 77.2 tok/s | reported | 513 | - GB | 2,048 | llama.cpp |
| Arc Pro B70 32GB | 5-bit | 8.8 tok/s | measured | 382 | - GB | 129,325 | 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.