M1 (8-core GPU, 8 GB)

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

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M1 (8-core GPU, 8 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile14.552260666666667133.8709728888889–9.648145671333332––sourced–source
M1 (8-core GPU, 8 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile40.41441422222222607.4231519333333–2.1677008980666663––sourced–source

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

← all hardware