Leaderboard - TokenMark Hardware Rankings

See how devices rank for local LLM inference. Compare Apple M4, RTX 4090, Snapdragon X Elite, AMD Strix, and more on the TokenMark leaderboard.

Snapshot 2026-09-28 · 207 configs · 94 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) · 145 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
Qwen3-30B-A3B-Instruct-2507	IQ4_XS	llama.cpp/vulkan	103.2 tok/s (prefill 1438.1)	512	Structured table	source
Qwen3-Coder 30B-A3B	Q4_K_S	llama.cpp/vulkan	98 tok/s (prefill 1406.5)	512	Structured table	source
Qwen3-Coder 30B-A3B	UD-Q4_K_XL	llama.cpp/vulkan	97.1 tok/s (prefill 1400)	512	Structured table	source
Qwen3-Coder 30B-A3B	IQ4_XS	llama.cpp/vulkan	90.4 tok/s (prefill 1372.3)	512	Structured table	source
Qwen3 30B-A3B NEO-MAX	IQ4_XS	llama.cpp/vulkan	87.4 tok/s (prefill 1396.1)	512	Structured table	source
Qwen3.6 35B-A3B	Q4_0	llama.cpp/vulkan	81.3 tok/s (prefill 1243.5)	512	Structured table	source
Qwen3-30B-A3B	UD-Q4_K_XL	llama.cpp/rocm	79.1 tok/s (prefill 687.9)		Structured table	source
Nemotron Cascade 2 30B-A3B	IQ4_XS	llama.cpp/vulkan	79 tok/s (prefill 1325.3)	512	Structured table	source
Gemma-4-26B-A4B	UD-Q4_K_XL	llama.cpp	78 tok/s		Owner-submitted	source
Ornith 1.5 35B-A3B	FP4		76.9 tok/s		Owner-submitted	source
Nemotron 3 Nano 30B-A3B	IQ4_XS	llama.cpp/vulkan	76 tok/s (prefill 1312.5)	512	Structured table	source
Qwen3.5 35B-A3B	IQ4_XS	llama.cpp/vulkan	75.2 tok/s (prefill 1170.3)	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) · 39 single-stream configs

Model	Quant	Backend	Decode	Context	Trust	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
Ornith-1.0-35B-AEON	NVFP4	vllm	84.8 tok/s		Structured table	source
Qwen3.6-35B-A3B	NVFP4	vllm	77.4 tok/s		Structured table	source
Qwen3.6-35B-A3B	Q4_K_XL	llama.cpp	62.7 tok/s		Structured table	source
Ornith-1.0-35B	Q8_0	llama.cpp	56.1 tok/s		Structured table	source
DeepSeek-V4-Flash-0731-JA-REAP-K216	EXL3-3BPW		55 tok/s	256000	Extracted, source-linked	source
Qwen3-Coder-Next-80B-A3B	Q4_K_XL	llama.cpp	50.1 tok/s		Structured table	source
Qwen3.6-35B-A3B		llama.cpp	48.2 tok/s		Structured table	source
Nemotron-3-Nano-30B-A3B		llama.cpp	47.9 tok/s		Structured table	source
Kimi-Linear-48B-A3B	Q8_0	llama.cpp	47.2 tok/s		Structured table	source
Qwen3.8-Flash-Next	NVFP4	vllm (speculative decode, mtp-2)	44.2 tok/s	262144	Extracted, source-linked	source
Nemotron-3-Nano-Omni-30B-A3B	NVFP4	vllm	41.7 tok/s		Structured table	source
Nemotron-3-Nano-30B-A3B	FP8	vllm	40.7 tok/s		Structured table	source

Apple M-series Max (MacBook Pro / Mac Studio Max) · 2 single-stream configs

Model	Quant	Backend	Decode	Context	Trust	Source
Qwen3.8-Flash-Next-REAP-288	MLX-4BIT	mlx/pmlx	37 tok/s		Extracted, source-linked	source
Qwen3.8-Flash-Next-REAP-288	MLX-4BIT	mlx	28 tok/s		Extracted, source-linked	source

Apple Mac Studio (M-series Ultra) · 3 single-stream configs

Model	Quant	Backend	Decode	Context	Trust	Source
GLM-5.3-Flash	MLX-4BIT	mlx	34.2 tok/s		Extracted, source-linked	source
DeepSeek-V4-Flash-0731-MXFP4-MLX-Abliterated	MXFP4	mlx	29.6 tok/s (prefill 454)	1048576	Extracted, source-linked	source
GLM-5.3-Flash Abliterated	MLX-4BIT	mlx (speculative decode, mtp)	24 tok/s (prefill 365)	16384	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.