RTX 4090M
8 records across 1 models (quants: Q8_0).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | 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 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 4090M | Qwen 3.5 9B | Q8_0 | llama.cpp (CUDA) | 40.3 | – | – | – | 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 |
All rows cite their source. Provenance: community 40018 sourced 1085