Contributors › drowzeys's local-LLM benchmark configs

drowzeys's local-LLM benchmark configs

Every tracked benchmark config measured by drowzeys: model, quant, backend, tokens per second, source-linked and trust-tiered.

Snapshot 2026-09-10 · 148 configs · 69 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

3 configs · 3 models · 6 stars · 34.2 tok/s best single-stream · drowzeys on github.

Configs measured by drowzeys

ModelQuantBackendDecodeContextTrustSource
GLM-5.3-FlashMLX-4BITmlx34.2 tok/sExtracted, source-linkedsource
DeepSeek-V4-Flash-0731-MXFP4-MLX-AbliteratedMXFP4mlx29.6 tok/s (prefill 454)1048576Extracted, source-linkedsource
GLM-5.3-Flash AbliteratedMLX-4BITmlx24 tok/s (prefill 365)16384Extracted, source-linkedsource

More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.