M2 Ultra (60-core GPU, 64 GB)

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

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M2 Ultra (60-core GPU, 64 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile59.480982703.2592348888888–1.6398754306666665––sourced–source
M2 Ultra (60-core GPU, 64 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile174.086613000000033290.1508422222223–0.3351846761111111––sourced–source
M2 Ultra (60-core GPU, 64 GB)qwen-2-5-14b-instruct Q4_K - Mediumllamafile34.21236922222223381.12729266666673–3.0647734165555556––sourced–source

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

← all hardware