community pool / model answer
Qwythos-9B-v2-GGUF
chat · empero-ai/Qwythos-9B-v2-GGUF
54.6 tok/s · model median · 30 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 4-bit | 51.1 tok/s | reported | - | 5.8 GB | 32,768 | llama.cpp |
| RTX 3060 12GB ×2 | 4-bit | 53.2 tok/s | measured | 456 | 9.8 GB | 131,072 | llama.cpp |
| RTX 3090 24GB | 4-bit | 78.5 tok/s | measured | 2,549 | - GB | 131,072 | llama.cpp |
| RX 7700 XT 12GB | 4-bit | 49.8 tok/s | reported | 305 | - GB | 2,048 | vllm |
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.