community pool / model answer
Qwopus3.6-27B-v2-GGUF
chat · Jackrong/Qwopus3.6-27B-v2-GGUF
18.2 tok/s · model median · 11 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 2080 Ti 11GB ×2 | 4-bit | 20.1 tok/s | reported | 1,409 | 19.3 GB | 98,304 | llama.cpp |
| RTX 3060 12GB ×2 | 4-bit | 17.7 tok/s | measured | 18,592 | 19.5 GB | 131,072 | llama.cpp |
| RTX 3090 24GB ×2 | 6-bit | 56.4 tok/s | reported | 533 | - GB | 262,144 | 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.