RTX 3060

30 records across 4 models (quants: Q4_0, Q4_K - Medium, Q8_0, as-published).

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
RTX 3060gpt-oss 20B MXFP4 MoE as-publishedllama.cpp (Vulkan)18.65324.21––tg1282025-11-18community–source
RTX 3060gpt-oss 20B MXFP4 MoE as-publishedllama.cpp (Vulkan)16.18184.9––tg1282025-11-18community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)80.592012.88––tg1282025-11-23community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)75.941815.7––tg1282025-11-23community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)73.711685.14––tg1282025-12-03community–source
RTX 3060llama 7B Q4_0llama.cpp (CUDA)70.782229.42––tg1282025-06-17community–source
RTX 3060llama 7B Q4_0llama.cpp (CUDA)68.382020.4––tg1282025-06-17community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)68.341122.04––tg1282025-12-03community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)67.111826.49––tg1282025-06-17community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)66.121715.17––tg1282025-08-23community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)65.631730.33––tg1282025-08-23community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)64.761681.81––tg1282025-06-17community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)54.281298.03––tg1282025-01-21community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)52.66428.54––tg1282025-11-26community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)50.23439.87––tg1282025-11-26community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)49.031059.76––tg1282025-03-20community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)20.18254.09––tg1282025-03-20community–source
RTX 3060llama 7B Q4_K - Mediumllama.cpp (Vulkan)11.8218.01––tg1282025-11-18community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)10.8190.15––tg1282025-03-20communitycontradictionsource
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)9.7972.76––tg1282025-12-03community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)9.4874.29––tg1282025-12-03community–source
RTX 3060llama 7B Q4_K - Mediumllama.cpp (Vulkan)9.41081.37––tg1282025-11-18community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)7.6991.04––tg1282025-12-03community–source
RTX 3060llama 7B Q4_0llama.cpp (Vulkan)7.3390.13––tg1282025-12-03community–source
RTX 3060llama 8B Q4_K - Mediumllama.cpp (Vulkan)12.11230.26––tg1282025-11-18community–source
RTX 3060llama 8B Q4_K - Mediumllama.cpp (Vulkan)9.061061.32––tg1282025-11-18community–source
RTX 3060qwen3moe 30B.A3B Q4_K - Mediumllama.cpp (Vulkan)22.79212.78––tg1282025-11-18community–source
RTX 3060qwen3moe 30B.A3B Q8_0llama.cpp (Vulkan)15.52171.43––tg1282025-11-18community–source
RTX 3060qwen3moe 30B.A3B Q4_K - Mediumllama.cpp (Vulkan)15.47113.21––tg1282025-11-18community–source
RTX 3060qwen3moe 30B.A3B Q8_0llama.cpp (Vulkan)8.6986.32––tg1282025-11-18community–source

All rows cite their source. Provenance: community 40018 sourced 1085

← all hardware