Qwen 3 4B

6 records across 1 hardware.

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M4 Max (40-core GPU, 64 GB)Qwen 3 4B Q4_G32MLX149.072838.42––2048–sourced–source
M4 Max (40-core GPU, 64 GB)Qwen 3 4B Q4MLX148.082976.68––2048–sourced–source
M4 Max (40-core GPU, 64 GB)Qwen 3 4B Q5MLX143.22736.15––2048–sourced–source
M4 Max (40-core GPU, 64 GB)Qwen 3 4B Q5_G32MLX142.982754.53––2048–sourced–source
M4 Max (40-core GPU, 64 GB)Qwen 3 4B Q6MLX136.582735.69––2048–sourced–source
M4 Max (40-core GPU, 64 GB)Qwen 3 4B Q8MLX111.551780.63––2048–sourced–source

← all models