M1 (7-core GPU, 16 GB)

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

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M1 (7-core GPU, 16 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile9.38748333333333283.93792277777777–14.82420303238889––sourced–source
M1 (7-core GPU, 16 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile37.872518722222225530.8859519722223–2.4528570579444446––sourced–source
M1 (7-core GPU, 16 GB)qwen-2-5-14b-instruct Q4_K - Mediumllamafile4.80667305555555640.612479388888886–30.980614497666668––sourced–source

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

← all hardware