Hardware › Mac Max local LLM benchmarks: 29 measured configs

Mac Max local LLM benchmarks: 29 measured configs

29 measured local-LLM configs on Apple M-series Max (MacBook Pro / Mac Studio Max); fastest 14B+ model Qwen3.6-35B-A3B at 151.1 tok/s. Official specs, Singapore prices read daily, every number linked to its source.

Snapshot 2026-10-16 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

Silicon: Apple M-series Max (MacBook Pro / Mac Studio Max). Official specs.

Quick answers

What is the fastest model on Mac Max?: Qwen3.6-35B-A3B at 151.1 tok/s single-stream (MLX-4BIT, mlx), source last checked 2026-09-29. Models under 14B parameters are left out of this answer. source
What is the fastest 100B+ model on Mac Max?: Qwen3.8-Flash-Next at 57.5 tok/s single-stream (Q4-INF, mlx), source last checked 2026-09-06. source
What is the largest model measured on Mac Max?: Qwen3.8-Flash-Next (177B parameters) at 57.5 tok/s single-stream (Q4-INF, mlx), source last checked 2026-09-06. source
How many configs does TokenMark track for Mac Max?: 29 single-stream configs across 14 models, each linked to the README or model card it came from.

Official specs

current lineup: M5 Max in the 14/16-inch MacBook Pro and the 2026 Mac Studio; previous generation M4 Max (2024) is what most published benchmarks were measured on (source)
max unified memory gb: 128 (source)
memory bandwidth gbps: 460 (32-core GPU) / 614 (40-core GPU) (source)
memory type: unified (source)
form factor: laptop (MacBook Pro 14/16-inch) or desktop (Mac Studio) (source)

Where to buy Apple M-series Max (MacBook Pro / Mac Studio Max) in Singapore

Read 17 Oct 2026 (SGT) from each seller's own product page. Prices in SGD. Overseas stores are converted at USD/SGD 1.2792 with 9% GST at import added; shipping is not included. Singapore sellers already include GST. List prices on the day, not a quote. No affiliate links.

Apple Mac Studio, M5 Max (base configs)

Apple (SG) (Official store, configure to order): S$3,499 to S$4,399

Apple MacBook Pro 14 or 16 inch, M5 Max (base configs)

Apple (SG) (Official store, configure to order): S$5,799 to S$6,999

Measured single-stream configs on Apple M-series Max (MacBook Pro / Mac Studio Max)

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
Qwen3-30B-A3B	Q4_K_M	llama.cpp	148.5 tok/s (prefill 3497)	512	Extracted, source-linked	source
Qwen3-30B-A3B	MLX-4BIT	mlx	147.2 tok/s (prefill 3458)	512	Extracted, source-linked	source
Qwen3.6-35B-A3B	Q4_K_M	llama.cpp	124.3 tok/s (prefill 3343)	512	Extracted, source-linked	source
Qwen3-8B	MLX-4BIT	mlx	110.5 tok/s (prefill 3151)	512	Extracted, source-linked	source
Qwen3-8B	Q4_K_M	llama.cpp	97.7 tok/s (prefill 2745)	512	Extracted, source-linked	source
gemma-3-12b	MLX-4BIT	mlx	66.9 tok/s (prefill 1835)	512	Extracted, source-linked	source
Qwen3-14B	MLX-4BIT	mlx	62.5 tok/s (prefill 1739)	512	Extracted, source-linked	source
gemma-3-12b	Q4_K_M	llama.cpp	61.5 tok/s (prefill 1721)	512	Extracted, source-linked	source
Qwen3.8-Flash-Next	Q4-INF	mlx	57.5 tok/s		Extracted, source-linked	source
Qwen3-14B	Q4_K_M	llama.cpp	57.4 tok/s (prefill 1584)	512	Extracted, source-linked	source
Gemma-4-12B		ollama	56.1 tok/s		Extracted, source-linked	source
Qwen3-4B	BF16	xwen	55.9 tok/s (prefill 3416)	3890	Extracted, source-linked	source
Qwen3.8-Flash-Next-REAP-288	MLX-4BIT	mlx (speculative decode, mtp)	52 tok/s	10240	Extracted, source-linked	source
Qwen3.8-Flash-Next	UD-Q4_K_XL	llama.cpp	41.4 tok/s (prefill 789)	530	Extracted, source-linked	source
mistral-small-3.1-24b	MLX-4BIT	mlx	41.1 tok/s (prefill 1051)	512	Extracted, source-linked	source
mistral-small-3.1-24b	Q4_K_M	llama.cpp	37.2 tok/s (prefill 977)	512	Extracted, source-linked	source
Qwen3.8-Flash-Next-REAP-288	MLX-4BIT	mlx/pmlx	37 tok/s		Extracted, source-linked	source
gemma-3-27b	MLX-4BIT	mlx	31.8 tok/s (prefill 854)	512	Extracted, source-linked	source
Qwen3.8-27B	MLX-4BIT	mlx	31.5 tok/s		Extracted, source-linked	source
Qwen3.6-35B-A3B	BF16	mlx	30.8 tok/s		Extracted, source-linked	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.