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 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 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
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| GLM-5.3-Flash | Mac Ultra | MLX-4BIT | mlx | 34.2 tok/s | Extracted, source-linked | source | |
| DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated | Mac Ultra | MXFP4 | mlx | 29.6 tok/s (prefill 454) | 1048576 | Extracted, source-linked | source |
| GLM-5.3-Flash Abliterated | Mac Ultra | MLX-4BIT | mlx (speculative decode, mtp) | 24 tok/s (prefill 365) | 16384 | Extracted, source-linked | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.