M5 Max (32-core GPU, 36 GB)

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

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M5 Max (32-core GPU, 36 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile61.634733222222216630.2577913333333–1.914077976777778––sourced–source
M5 Max (32-core GPU, 36 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile228.993727777777763620.6608126666665–0.32193552311111107––sourced–source
M5 Max (32-core GPU, 36 GB)qwen-2-5-14b-instruct Q4_K - Mediumllamafile34.28566722222222343.244466–3.5801585140000003––sourced–source

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

← all hardware