RTX 3060 12GB
6 records across 3 models (quants: Q4_K, Q4_K_M).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | gemma4 12B Q4_KM | Q4_K_M | llama.cpp (CUDA) | 33.34 | 609.26 | – | – | – | 2026-06-09 | community | – | source |
| RTX 3060 12GB | Qwen3 14B 14B | Q4_K | llama.cpp | 31.2 | 972.6 | – | – | 4096 | – | sourced | – | source |
| RTX 3060 12GB | Qwen3 14B 14B | Q4_K | llama.cpp | 22.7 | 678.2 | – | – | 16384 | – | sourced | – | source |
| RTX 3060 12GB | Qwen3 8B 8B | Q4_K | llama.cpp | 55.2 | 1696.8 | – | – | 4096 | – | sourced | – | source |
| RTX 3060 12GB | Qwen3 8B 8B | Q4_K | llama.cpp | 42.0 | 1119.2 | – | – | 16384 | – | sourced | – | source |
| RTX 3060 12GB | Qwen3 8B 8B | Q4_K | llama.cpp | 31.9 | 764.7 | – | – | 32768 | – | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085