M1 Ultra (GPU count not published, 128 GB)

3 records across 3 models (quants: Q4_K - Medium).

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M1 Ultra (GPU count not published, 128 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile15.2484754444444471.55644355555556–17.47675613911111––sourced–source
M1 Ultra (GPU count not published, 128 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile57.07094177777779283.7757922222222–4.787078634222223––sourced–source
M1 Ultra (GPU count not published, 128 GB)qwen-2-5-14b-instruct Q4_K - Mediumllamafile7.988316333333334538.83732133333333–32.935429014111115––sourced–source

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

← all hardware