Hardware · Apple Silicon

What AI models can the Apple M2 Max (32 GB) run?

Unified memory: 32.0 GB
Usable for models: 21.4 GB
Memory bandwidth: 400 GB/s
FP16 compute: 13.6 TFLOPS
Released: 2023

macOS lets the GPU use roughly two-thirds to three-quarters of unified memory by default, so we plan around that figure rather than the full 32.0 GB.

Specifications

Maker	Apple Silicon
Type	Apple silicon (system on a chip)
Chip	Apple M2 Max
Unified memory	32.0 GB
Usable for AI models	21.4 GB
Memory bandwidth	400 GB/s
FP16 compute	13.6 TFLOPS
Interface	UNIFIED
Released	2023

3 products with the Apple M2 Max (32 GB)

MacBook Pro (14-inch, 2023) (M2 Pro or M2 Max)Apple · Laptop · 16, 32, 64 or 96 GB · from $1,999Maker’s page (opens in a new tab)
MacBook Pro (16-inch, 2023) (M2 Pro or M2 Max)Apple · Laptop · 16, 32, 64 or 96 GB · from $2,499Maker’s page (opens in a new tab)
Mac Studio (2023) (M2 Max or M2 Ultra)Apple · Desktop · 32, 64, 96, 128 or 192 GB · from $1,999Maker’s page (opens in a new tab)

Best LLMs for the Apple M2 Max (32 GB)

Grade · points	Model	Quant	Memory	Speed	Fit
94 ptsExcellent (S) · 94 of 100 points: Model quality 40.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Gemma 4 26B-A4BGoogle	`Q5_K_M`	21.0 GB	46.0 tok/s	Tight fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 35.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3.6 35B-A3BAlibaba	`Q3_K_M`	20.1 GB	91.1 tok/s	Tight fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 35.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3.5 35B-A3BAlibaba	`Q3_K_M`	20.1 GB	91.1 tok/s	Tight fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 40.9/45, Memory fit 24.0/25, Speed 9.3/15, Memory use 15.0/15	Qwen3.8 27BAlibaba	`Q4_K_M`	19.8 GB	15.2 tok/s	Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 40.2/45, Memory fit 24.0/25, Speed 9.3/15, Memory use 15.0/15	Qwen3.6 27BAlibaba	`Q4_K_M`	19.8 GB	15.2 tok/s	Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GLM-4.7 Flash (30B-A3B)Zhipu AI	`Q3_K_M`	18.1 GB	91.1 tok/s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	North Mini Code 1.0 (30B-A3B)Cohere	`Q4_K_M`	21.2 GB	70.5 tok/s	Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	DiffusionGemma 26B-A4B ITGoogle	`Q5_K_M`	21.1 GB	43.7 tok/s	Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Ornith 1.5 35B-A3BDeepReinforce	`Q3_K_M`	20.1 GB	91.1 tok/s	Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 9.3/15, Memory use 15.0/15	Qwen3.5 27BAlibaba	`Q4_K_M`	19.8 GB	15.2 tok/s	Tight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Apodex 1.1 Mini (35B-A3B)Apodex	`Q3_K_M`	20.1 GB	91.1 tok/s	Tight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Ornith 1.0 35B-A3BDeepReinforce	`Q3_K_M`	20.1 GB	91.1 tok/s	Tight fit

Best Image models for the Apple M2 Max (32 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	FLUX.2 [klein] 4BBlack Forest Labs	`FP16`	18.1 GB	7.4 s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 37.0/45, Memory fit 23.0/25, Speed 13.7/15, Memory use 15.0/15	FLUX.2 [klein] 9BBlack Forest Labs	`FP8`	19.9 GB	12 s	Tight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 11.7/15, Memory use 13.5/15	Z-Image TurboAlibaba (Tongyi)	`FP8`	12.6 GB	17 s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 27.3/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 15.0/15	Stable Diffusion 3.5 Large TurboStability AI	`FP8`	16.3 GB	11 s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 30.9/45, Memory fit 23.0/25, Speed 13.0/15, Memory use 15.0/15	FLUX.1 [schnell]Black Forest Labs	`FP8`	19.6 GB	13 s	Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 36.2/45, Memory fit 23.0/25, Speed 5.3/15, Memory use 15.0/15	FLUX.1 Krea [dev]Black Forest Labs	`FP8`	19.6 GB	79 s	Tight fit

Best Video models for the Apple M2 Max (32 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 15.0/15	LTX-Video 2BLightricks	`FP16`	17.5 GB	3.1 min	Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 31.0/45, Memory fit 23.0/25, Speed 2.3/15, Memory use 15.0/15	Wan 2.1 I2V 14B 480PAlibaba	`Q4 GGUF`	20.6 GB	2.2 h	Tight fit
70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 15.0/15	CogVideoX 5BZhipu AI	`FP8`	14.3 GB	19.8 min	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 15.0/15	CogVideoX 5B I2VZhipu AI	`FP8`	14.9 GB	19.8 min	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 32.6/45, Memory fit 18.0/25, Speed 3.8/15, Memory use 15.0/15	FramePack I2V (HunyuanVideo 13B)lllyasviel	`FP8`	19.6 GB	46.3 min	Tight fit

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.