community pool / model answer
Qwen3.8-27B-GGUF
chat · AtomicChat/Qwen3.8-27B-GGUF
46.1 tok/s · model median · 3 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 5070 12GB | 2-bit | 46 tok/s | reported | 544 | 10.1 GB | 2,048 | llama.cpp |
| RTX 5090 32GB | 6-bit | 98.7 tok/s | reported | 279 | 29.4 GB | 131,000 | 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.