RTX 3080 Ti
5 records across 2 models (quants: Q4_K).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 3080 Ti | Qwen3 14B 14B | Q4_K | llama.cpp | 69.9 | 2600.1 | – | – | 4096 | – | sourced | – | source |
| RTX 3080 Ti | Qwen3 14B 14B | Q4_K | llama.cpp | 52.3 | 1773.9 | – | – | 16384 | – | sourced | – | source |
| RTX 3080 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 115.2 | 4211.7 | – | – | 4096 | – | sourced | – | source |
| RTX 3080 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 87.9 | 2658.5 | – | – | 16384 | – | sourced | – | source |
| RTX 3080 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 68.1 | 1761.2 | – | – | 32768 | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085