Qwen 3.5 9B
29 records across 4 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 81.58 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 77.44 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 75.55 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 75.01 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 74.85 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 72.79 | – | – | – | 65536 | 2026-04-01 | community | – | source |
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 63.44 | – | – | – | 65536 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 63.12 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 Ti | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 61.47 | – | – | – | 65536 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 61.0 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 60.28 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 56.91 | – | – | – | 65536 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 56.91 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 56.82 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 53.21 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 52.7 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 52.4 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 52.0 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 49.27 | – | – | – | 65536 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 49.0 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 48.2 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 44.9 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 44.79 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 42.45 | – | – | – | 65536 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 40.3 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 35.63 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 34.5 | – | – | – | 32768 | 2026-04-01 | community | – | source |
| RTX 3090 | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 33.43 | – | – | – | 65536 | 2026-04-01 | community | – | source |
| M6 | Qwen 3.5 9B | unspecified | MLX | 30.3 | – | – | – | 32768 | 2026-10-03 | community | – | source |