community pool / model answer
Hy3-GGUF
chat · AngelSlim/Hy3-GGUF
35.8 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| CMP 170HX 64GB ×2 | 2-bit | 34.9 tok/s | measured | - | 98.6 GB | 32,768 | llama.cpp |
| RTX 5090 32GB ×4 | 1-bit | 87.1 tok/s | reported | 50 | 121.6 GB | 131,072 | 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.