RTX 4060
4 records across 1 models (quants: Q4_0).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 4060 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 60.01 | 2358.03 | – | – | tg128 | 2025-11-04 | community | – | source |
| RTX 4060 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 59.53 | 2135.66 | – | – | tg128 | 2025-11-04 | community | – | source |
| RTX 4060 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 53.8 | 1908.24 | – | – | tg128 | 2026-10-10 | community | – | source |
| RTX 4060 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 52.58 | 1793.16 | – | – | tg128 | 2026-10-10 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085