M2 Pro (16-core GPU, 32 GB)

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

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M2 Pro (16-core GPU, 32 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile23.809723111111115208.68323722222223–6.06785997211111––sourced–source
M2 Pro (16-core GPU, 32 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile91.452819444444441281.403522111111–0.9141989862222222––sourced–source

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

← all hardware