qwen3moe 30B.A3B
5 records across 2 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 5090 | qwen3moe 30B.A3B 30B-A3B | Q4_K_M | llama.cpp | 134.18 | 4081.2 | – | – | 1024 | 2026-09 | community | – | source |
| RTX 3060 | qwen3moe 30B.A3B | Q4_K - Medium | llama.cpp (Vulkan) | 22.79 | 212.78 | – | – | tg128 | 2025-11-18 | community | – | source |
| RTX 3060 | qwen3moe 30B.A3B | Q8_0 | llama.cpp (Vulkan) | 15.52 | 171.43 | – | – | tg128 | 2025-11-18 | community | – | source |
| RTX 3060 | qwen3moe 30B.A3B | Q4_K - Medium | llama.cpp (Vulkan) | 15.47 | 113.21 | – | – | tg128 | 2025-11-18 | community | – | source |
| RTX 3060 | qwen3moe 30B.A3B | Q8_0 | llama.cpp (Vulkan) | 8.69 | 86.32 | – | – | tg128 | 2025-11-18 | community | – | source |