RTX 4080
12 records across 3 models (quants: MXFP4, Q4_K).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 4080 | gpt-oss 20B 20B | MXFP4 | llama.cpp | 136.5 | 6218.5 | – | – | 4096 | – | sourced | – | source |
| RTX 4080 | gpt-oss 20B 20B | MXFP4 | llama.cpp | 120.2 | 4329.2 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 | gpt-oss 20B 20B | MXFP4 | llama.cpp | 106.0 | 2831.1 | – | – | 32768 | – | sourced | – | source |
| RTX 4080 | gpt-oss 20B 20B | MXFP4 | llama.cpp | 81.3 | 1559.0 | – | – | 65536 | – | sourced | – | source |
| RTX 4080 | gpt-oss 20B 20B | MXFP4 | llama.cpp | 60.0 | 898.5 | – | – | 131072 | – | sourced | – | source |
| RTX 4080 | Qwen3 14B 14B | Q4_K | llama.cpp | 62.0 | 3574.7 | – | – | 4096 | – | sourced | – | source |
| RTX 4080 | Qwen3 14B 14B | Q4_K | llama.cpp | 51.2 | 2295.1 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 | Qwen3 14B 14B | Q4_K | llama.cpp | 40.6 | 1395.7 | – | – | 32768 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 102.7 | 6177.9 | – | – | 4096 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 77.9 | 3809.8 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 59.0 | 1968.4 | – | – | 32768 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 39.0 | 937.9 | – | – | 65536 | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085