M3 (10-core GPU, 16 GB)

2 records across 2 models (quants: Q4_K - Medium).

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M3 (10-core GPU, 16 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile13.499802861111112138.71456447222224–9.024639849583332––sourced–source
M3 (10-core GPU, 16 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile67.18826562222223931.5106880888889–1.4093825610888888––sourced–source

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

← all hardware