Contributors › lhl's local-LLM benchmark configs

lhl's local-LLM benchmark configs

Every tracked benchmark config measured by lhl: 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.

17 configs · 15 models · 257 stars · 79.1 tok/s best single-stream · lhl on github.

Configs measured by lhl

Model	Hardware	Quant	Backend	Decode	Context	Trust	Source
Qwen3-30B-A3B	Strix Halo	UD-Q4_K_XL	llama.cpp/rocm	79.1 tok/s (prefill 687.9)		Structured table	source
llama-2-7b	Strix Halo	Q4_0	llama.cpp/rocm	53 tok/s (prefill 1327)		Structured table	source
llama-2-7b	Strix Halo	Q4_K_M	llama.cpp/rocm	50.4 tok/s (prefill 1083)		Structured table	source
gpt-oss-20b-F16	Strix Halo		llama.cpp/rocm	47.8 tok/s (prefill 1213.3)		Structured table	source
shisa-v2-llama3.1-8b.i1	Strix Halo	Q4_K_M	llama.cpp/rocm	43.5 tok/s (prefill 878.2)		Structured table	source
gpt-oss-120b-F16	Strix Halo		llama.cpp/rocm	33.9 tok/s (prefill 534.1)		Structured table	source
gpt-oss-120b	Strix Halo	MXFP4	llama.cpp/vulkan	31.5 tok/s	32768	Extracted, source-linked	source
GLM-4.5-Air	Strix Halo	UD-Q4_K_XL	llama.cpp/vulkan	23.4 tok/s (prefill 179.9)		Structured table	source
dots.llm1.inst	Strix Halo	UD-Q4_K_XL	llama.cpp/rocm	22.7 tok/s (prefill 182)		Structured table	source
Llama-4-Scout-17B-16E-Instruct	Strix Halo	UD-Q4_K_XL	llama.cpp/rocm	20.2 tok/s (prefill 306.4)		Structured table	source
Hunyuan-A13B-Instruct	Strix Halo	UD-Q6_K_XL	llama.cpp/rocm	18.4 tok/s (prefill 297.5)		Structured table	source
gpt-oss-120b	Strix Halo	MXFP4	llama.cpp/rocm	17.8 tok/s	32768	Extracted, source-linked	source
Qwen3-235B-A22B-Instruct-2507	Strix Halo	UD-Q3_K_XL	llama.cpp/vulkan	15.9 tok/s (prefill 117.1)		Structured table	source
Mistral-Small-3.1-24B-Instruct-2503	Strix Halo	UD-Q4_K_XL	llama.cpp/rocm	14.7 tok/s (prefill 368.5)		Structured table	source
gemma-3-27b-it	Strix Halo	UD-Q4_K_XL	llama.cpp/rocm	12.1 tok/s (prefill 302.2)		Structured table	source
Qwen3-32B	Strix Halo	Q8_0	llama.cpp/rocm	6.4 tok/s (prefill 226.1)		Structured table	source
shisa-v2-llama3.3-70b.i1	Strix Halo	Q4_K_M	llama.cpp/rocm	5.1 tok/s (prefill 94.7)		Structured table	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.