RTX 4070 Ti
7 records across 3 models (quants: Q4_0, Q4_K).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 4070 Ti | llama 7B | Q4_0 | llama.cpp (Vulkan) | 113.52 | 5515.26 | – | – | tg128 | 2026-01-17 | community | – | source |
| RTX 4070 Ti | llama 7B | Q4_0 | llama.cpp (Vulkan) | 110.53 | 4981.44 | 221 | – | tg128 | 2026-01-17 | community | – | source |
| RTX 4070 Ti | Qwen3 14B 14B | Q4_K | llama.cpp | 45.8 | 2866.6 | – | – | 4096 | – | sourced | – | source |
| RTX 4070 Ti | Qwen3 14B 14B | Q4_K | llama.cpp | 37.8 | 1951.4 | – | – | 16384 | – | sourced | – | source |
| RTX 4070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 75.8 | 4877.7 | – | – | 4096 | – | sourced | – | source |
| RTX 4070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 57.6 | 2274.8 | – | – | 16384 | – | sourced | – | source |
| RTX 4070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 42.1 | 1099.7 | – | – | 32768 | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085