M5 (10-core GPU, 32 GB)

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

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M5 (10-core GPU, 32 GB)llama-3-1-8b-instruct Q4_K - Mediumllamafile22.29346603703704210.70696922222223–5.997633993703704––sourced–source
M5 (10-core GPU, 32 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile98.370041722222241271.5481898333337–0.989687108888889––sourced–source
M5 (10-core GPU, 32 GB)qwen-2-5-14b-instruct Q4_K - Mediumllamafile11.536774722222225110.4192515–11.637239780333331––sourced–source

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

← all hardware