community pool / model answer
Hy-MT2-7B
chat · tencent/Hy-MT2-7B
31 tok/s · model median · 7 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB | 4-bit | 98.1 tok/s | reported | - | - GB | 1,024 | llama.cpp |
| RX 570 4GB ×2 | 4-bit | 29.3 tok/s | measured | 75 | - GB | 2,048 | 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.