KAT-Coder-V2.5
4 records across 2 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 5090 | KAT-Coder-V2.5 | APEX-I-MiniPlus V2.1 | llama.cpp | 247 | 2800 | – | – | – | 2026-09-18 | community | – | source |
| RTX 5080 | KAT-Coder-V2.5 35B | Q6_K | llama.cpp (CUDA) | 71.63 | 779.29 | – | – | – | 2026-08 | community | – | source |
| RTX 5080 | KAT-Coder-V2.5 35B | Q6_K | llama.cpp (CUDA) | 70.29 | 1024.01 | – | – | – | 2026-08 | community | – | source |
| RTX 5080 | KAT-Coder-V2.5 35B | Q6_K | llama.cpp (CUDA) | 69.93 | – | – | – | – | 2026-08 | community | – | source |