Contributors › hogeheer's local-LLM benchmark configs

hogeheer's local-LLM benchmark configs

Every tracked benchmark config measured by hogeheer: 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.

41 configs · 29 models · 366 stars · 266 tok/s best single-stream · hogeheer on github.

Configs measured by hogeheer

Model	Hardware	Quant	Backend	Decode	Context	Trust	Source
Qwen3 0.6B	Strix Halo	Q8_0	llama.cpp/vulkan	266 tok/s (prefill 13112)	512	Structured table	source
Qwen3 0.6B	Strix Halo	Q8_0	llama.cpp/rocm	208.7 tok/s (prefill 4666.1)	512	Structured table	source
LFM2.5 8B-A1B	Strix Halo	Q4_K_M	llama.cpp/vulkan	176.5 tok/s (prefill 3398.4)	512	Structured table	source
Qwen3-30B-A3B-Instruct-2507	Strix Halo	IQ4_XS	llama.cpp/vulkan	103.2 tok/s (prefill 1438.1)	512	Structured table	source
Qwen3-Coder 30B-A3B	Strix Halo	Q4_K_S	llama.cpp/vulkan	98 tok/s (prefill 1406.5)	512	Structured table	source
Qwen3-Coder 30B-A3B	Strix Halo	UD-Q4_K_XL	llama.cpp/vulkan	97.1 tok/s (prefill 1400)	512	Structured table	source
Qwen3-Coder 30B-A3B	Strix Halo	IQ4_XS	llama.cpp/vulkan	90.4 tok/s (prefill 1372.3)	512	Structured table	source
Qwen3 30B-A3B NEO-MAX	Strix Halo	IQ4_XS	llama.cpp/vulkan	87.4 tok/s (prefill 1396.1)	512	Structured table	source
Qwen3.6-35B-A3B	Strix Halo	Q4_0	llama.cpp/vulkan	81.3 tok/s (prefill 1243.5)	512	Structured table	source
Nemotron Cascade 2 30B-A3B	Strix Halo	IQ4_XS	llama.cpp/vulkan	79 tok/s (prefill 1325.3)	512	Structured table	source
Nemotron-3-Nano-30B-A3B	Strix Halo	IQ4_XS	llama.cpp/vulkan	76 tok/s (prefill 1312.5)	512	Structured table	source
Qwen3.5-35B-A3B	Strix Halo	IQ4_XS	llama.cpp/vulkan	75.2 tok/s (prefill 1170.3)	512	Structured table	source
Gemma 4 26B-A4B IT QAT	Strix Halo	UD-Q4_K_XL	llama.cpp/vulkan	74.8 tok/s (prefill 1432)	512	Structured table	source
Qwen3-Coder 30B-A3B	Strix Halo	UD-Q4_K_XL	llama.cpp/rocm	73.7 tok/s (prefill 1285.3)	512	Structured table	source
Qwen-AgentWorld-35B-A3B	Strix Halo	IQ4_XS	llama.cpp/vulkan	65.7 tok/s (prefill 1182.8)	512	Structured table	source
Qwen3.5-35B-A3B	Strix Halo	Q4_K_M	llama.cpp/vulkan	64.9 tok/s (prefill 1080)	512	Structured table	source
Nemotron 3 Nano Omni 30B-A3B Reasoning	Strix Halo	MXFP4	llama.cpp/vulkan	64.3 tok/s (prefill 1286.2)	512	Structured table	source
Qwen3.6-35B-A3B	Strix Halo	Q4_K_M	llama.cpp/vulkan	63.8 tok/s (prefill 1064)	512	Structured table	source
Qwen3-Coder-Next-80B-A3B	Strix Halo	IQ4_XS	llama.cpp/vulkan	61.9 tok/s (prefill 739)	512	Structured table	source
Nemotron Labs Audex 30B-A3B text-only	Strix Halo	MXFP4	llama.cpp/vulkan	60.7 tok/s (prefill 1318.5)	512	Structured table	source
Qwen3.6-35B-A3B	Strix Halo	Q4_K_M	ollama/vulkan	60.6 tok/s (prefill 793.1)	2048	Structured table	source
NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning	Strix Halo	MXFP4	llama.cpp/vulkan	56.6 tok/s (prefill 1277.6)	512	Structured table	source
Qwen3-Next 80B-A3B	Strix Halo	UD-Q4_K_XL	llama.cpp/vulkan	54.9 tok/s (prefill 657)	512	Structured table	source
Qwen3.5-35B-A3B	Strix Halo	Q4_K_M	llama.cpp/rocm	54.7 tok/s (prefill 1047)	512	Structured table	source
gemma-4-26B-A4B-it	Strix Halo	Q4_K_M	llama.cpp/vulkan	54.2 tok/s (prefill 1323.4)	512	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.