TokenMark: Local AI Config Tracker for Strix Halo & DGX Spark

Measured tok/s configs for local LLMs on AMD Strix Halo, NVIDIA DGX Spark and Apple Mac, source-linked and updated daily. One searchable leaderboard.

Snapshot 2026-10-04 · 254 configs · 116 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

AMD Strix Halo (Ryzen AI Max+ 395) · 159 single-stream configs

Model	Quant	Backend	Decode	Context	Trust	Source
Qwen3 0.6B	Q8_0	llama.cpp/vulkan	266 tok/s (prefill 13112)	512	Structured table	source
Qwen3 0.6B	Q8_0	llama.cpp/rocm	208.7 tok/s (prefill 4666.1)	512	Structured table	source
LFM2.5 8B-A1B	Q4_K_M	llama.cpp/vulkan	176.5 tok/s (prefill 3398.4)	512	Structured table	source
Ornith-1.5-35B-A3B	FP4	(speculative decode, mtp)	105.6 tok/s		Owner-submitted	source
Qwen3-30B-A3B-Instruct-2507	IQ4_XS	llama.cpp/vulkan	103.2 tok/s (prefill 1438.1)	512	Structured table	source

AMD Gorgon Halo (Ryzen AI Max+ PRO 495) · 0 single-stream configs

No single-stream configs recorded yet.

NVIDIA DGX Spark (GB10) · 46 single-stream configs

Model	Quant	Backend	Decode	Context	Trust	Source
Qwen3 1.7B	Q4_K_M	llama.cpp	146.1 tok/s	2048	Extracted, source-linked	source
Qwen3.6-35B-heretic	NVFP4	vllm	96 tok/s		Structured table	source
Qwen3.6-35B-A3B-NVFP4-Fast (Unsloth)	NVFP4	vllm	92.6 tok/s		Structured table	source
GPT-OSS-20B	Q4_K_XL	llama.cpp	90.5 tok/s		Structured table	source
Ministral 3B	Q4_K_M	llama.cpp	86.6 tok/s	2048	Extracted, source-linked	source

Apple M-series Max (MacBook Pro / Mac Studio Max) · 23 single-stream configs

Model	Quant	Backend	Decode	Context	Trust	Source
llama-3.2-1b	MLX-4BIT	mlx	527.7 tok/s (prefill 17477)	512	Extracted, source-linked	source
llama-3.2-1b	Q4_K_M	llama.cpp	439.6 tok/s (prefill 16968)	512	Extracted, source-linked	source
qwen3-4b	MLX-4BIT	mlx	186 tok/s (prefill 5506)	512	Extracted, source-linked	source
qwen3-4b	Q4_K_M	llama.cpp	159.7 tok/s (prefill 4973)	512	Extracted, source-linked	source
qwen3.6-35b-a3b	MLX-4BIT	mlx	151.1 tok/s (prefill 3333)	512	Extracted, source-linked	source

Apple Mac Studio (M-series Ultra) · 7 single-stream configs

Model	Quant	Backend	Decode	Context	Trust	Source
Qwen3.6 35B-A3B	MLX-4BIT	mlx	109.1 tok/s (prefill 6012)	32000	Extracted, source-linked	source
Qwen3.8-Flash-Next	MLX-4BIT	mlx (speculative decode, mtp)	76.4 tok/s		Extracted, source-linked	source
Qwen3 14B	MLX-4BIT	mlx	55.4 tok/s (prefill 2278)	32000	Extracted, source-linked	source
Qwen3.8 27B	MLX-4BIT	mlx	42.6 tok/s (prefill 1526)	32000	Extracted, source-linked	source
GLM-5.3-Flash	MLX-4BIT	mlx	34.2 tok/s		Extracted, source-linked	source

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