Contributors › julianmb's local-LLM benchmark configs

julianmb's local-LLM benchmark configs

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

Snapshot 2026-09-16 · 158 configs · 75 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

10 configs · 4 models · 211 stars · 76.9 tok/s best single-stream · julianmb on github.

Configs measured by julianmb

Model	Quant	Backend	Decode	Context	Trust	Source
Ornith 1.5 35B-A3B	FP4		76.9 tok/s		Owner-submitted	source
Ornith 1.5 35B-A3B	Q4_K_M		71.6 tok/s		Owner-submitted	source
Qwen 3.8 27B	FP4		33.8 tok/s		Owner-submitted	source
DeepSeek V4 Flash 284B	IQ2_XXS		32 tok/s		Owner-submitted	source
Qwen 3.8 27B	FP4		26.9 tok/s	32768	Owner-submitted	source
Qwen3.8-27B-DFlash2	Q4_K_M	vulkan	21.2 tok/s (prefill 211)	32768	Owner-submitted	source
Qwen 3.8 27B	FP8	llama.cpp	19 tok/s		Owner-submitted	source
Qwen 3.8 27B	Q4_K_M		12.4 tok/s		Owner-submitted	source
Qwen 3.8 27B	Q4_K_M	llama.cpp	12.3 tok/s	32768	Owner-submitted	source
Qwen 3.8 27B	FP16	llama.cpp	5 tok/s		Owner-submitted	source

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