Qwen3.6-35B-A3B-APEX-MTP-I-Balanced
4 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Radeon 8060S | Qwen3.6-35B-A3B-APEX-MTP-I-Balanced | Q5_K_M | llama.cpp (Vulkan) | 80.89 | – | – | – | – | 2026-08-18 | community | – | source |
| Radeon 8060S | Qwen3.6-35B-A3B-APEX-MTP-I-Balanced | Q5_K_M | llama.cpp (ROCm) | 69.47 | – | – | – | – | 2026-08-18 | community | – | source |
| Radeon 8060S | Qwen3.6-35B-A3B-APEX-MTP-I-Balanced | Q5_K_M | llama.cpp (Vulkan) | 66.86 | – | – | – | – | 2026-08-18 | community | – | source |
| Radeon 8060S | Qwen3.6-35B-A3B-APEX-MTP-I-Balanced | Q5_K_M | llama.cpp (ROCm) | 56.41 | – | – | – | – | 2026-08-18 | community | – | source |