community pool / model answer
KAT-Coder-V2.5-Dev
code · Kwaipilot/KAT-Coder-V2.5-Dev
75 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Radeon AI Pro R9700 32GB ×3 | 8-bit | 75.8 tok/s | reported | 344 | 42.8 GB | 787 | llama.cpp |
| Ryzen AI Max 395 128GB | 4-bit | 70.3 tok/s | reported | 1,359 | - GB | 787 | 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.