community pool / model answer
Qwopus3.6-35B-A3B-v1-MTP-GGUF
chat · Jackrong/Qwopus3.6-35B-A3B-v1-MTP-GGUF
92.8 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 4-bit | 91.6 tok/s | measured | 2,374 | 21 GB | 32,768 | 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.