community pool / model answer
ThinkingCap-Qwen3.6-27B
chat · bottlecapai/ThinkingCap-Qwen3.6-27B
56.1 tok/s · model median · 9 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B70 32GB | 4-bit | 27.5 tok/s | reported | - | - GB | 204,800 | llama.cpp |
| Arc Pro B70 32GB | 5-bit | 26.3 tok/s | reported | - | - GB | 131,072 | llama.cpp |
| Arc Pro B70 32GB | 6-bit | 27.9 tok/s | reported | - | - GB | 131,072 | llama.cpp |
| RTX 3090 24GB ×2 | 8-bit | 58.6 tok/s | measured | 386 | - GB | 131,072 | 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.