glm4moe 106B.A12B
2 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Radeon RX 7900 XTX | glm4moe 106B.A12B | Q3_K - Medium | llama.cpp (ROCm) | 13.61 | 263.73 | – | – | tg128 | 2026-03-21 | community | – | source |
| Radeon RX 7900 XTX | glm4moe 106B.A12B | Q3_K - Medium | llama.cpp (Vulkan) | 10.35 | 252.83 | – | – | tg128 | 2026-03-21 | community | – | source |