Hardware · Apple Silicon

What AI models can the Apple M3 Pro (18 GB) run?

Unified memory: 18.0 GB
Usable for models: 12.1 GB
Memory bandwidth: 150 GB/s
FP16 compute: 7.4 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 18.0 GB.

Specifications

Maker	Apple Silicon
Type	Apple silicon (system on a chip)
Chip	Apple M3 Pro
Unified memory	18.0 GB
Usable for AI models	12.1 GB
Memory bandwidth	150 GB/s
FP16 compute	7.4 TFLOPS
Interface	UNIFIED
Released	2023

2 products with the Apple M3 Pro (18 GB)

MacBook Pro (14-inch, M3 Pro or M3 Max, Nov 2023)Apple · Laptop · 18, 36, 48, 64, 96 or 128 GB · from $1,999Maker’s page (opens in a new tab)
MacBook Pro (16-inch, Nov 2023) (M3 Pro or M3 Max)Apple · Laptop · 18, 36, 48, 64, 96 or 128 GB · from $2,499Maker’s page (opens in a new tab)

Best LLMs for the Apple M3 Pro (18 GB)

Grade · points	Model	Quant	Memory	Speed	Fit
84 ptsGreat (A) · 84 of 100 points: Model quality 35.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 15.0/15	Gemma 4 12BGoogle	`Q4_K_M`	9.5 GB	13.3 tok/s	Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 14.8/15	Ornith 1.5 9BDeepReinforce	`Q4_K_M`	7.7 GB	16.4 tok/s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 14.8/15	Qwen3.5 9BAlibaba	`Q4_K_M`	7.7 GB	16.4 tok/s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q6_K`	8.3 GB	42.3 tok/s	Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 14.8/15	Ornith 1.0 9BDeepReinforce	`Q4_K_M`	7.7 GB	16.4 tok/s	Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 10.0/15, Memory use 14.0/15	TMax 9BAi2	`Q4_K_M`	7.3 GB	17.7 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 14.5/15	UI-Mate 9BTencent	`Q4_K_M`	7.6 GB	16.8 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 14.5/15	UI-Venus 2 9BAnt Group (inclusionAI)	`Q4_K_M`	7.6 GB	16.8 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 10.1/15, Memory use 15.0/15	Granite 4.2 8BIBM	`Q4_K_M`	8.3 GB	18.0 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.7/15	LFM2.5 8B-A1BLiquid AI	`Q5_K_M`	7.7 GB	43.7 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 12.6/15	Gemma 4 E4BGoogle	`Q4_K_M`	6.6 GB	19.8 tok/s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15	Kimi-VL A3B Thinking 2506Moonshot AI	`Q4_K_M`	11.8 GB	26.4 tok/s	Tight fit

Best Image models for the Apple M3 Pro (18 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 34.4/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 15.0/15	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	10.2 GB	10 s	Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 35.2/45, Memory fit 25.0/25, Speed 8.0/15, Memory use 15.0/15	Z-Image TurboAlibaba (Tongyi)	`Q4 GGUF`	10.1 GB	35 s	Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 37.0/45, Memory fit 18.0/25, Speed 10.7/15, Memory use 15.0/15	FLUX.2 [klein] 9BBlack Forest Labs	`FP8`	11.7 GB	20 s	Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	SDXL-Lightning (4-step)ByteDance	`FP16`	8.9 GB	8.1 s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 34.3/45, Memory fit 25.0/25, Speed 3.1/15, Memory use 15.0/15	Z-ImageAlibaba (Tongyi)	`Q4 GGUF`	10.1 GB	3.9 min	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 15.0/15	Juggernaut XL v9RunDiffusion	`FP16`	8.9 GB	52 s	Runs well

Best Video models for the Apple M3 Pro (18 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
72 ptsGreat (A) · 72 of 100 points: Model quality 22.1/45, Memory fit 23.0/25, Speed 12.5/15, Memory use 15.0/15	LTX-Video 2BLightricks	`FP8`	10.8 GB	4.4 min	Tight fit
65 ptsGood (B) · 65 of 100 points: Model quality 19.8/45, Memory fit 23.0/25, Speed 8.0/15, Memory use 15.0/15	CogVideoX 2BZhipu AI	`FP8`	11.0 GB	10.4 min	Tight fit
63 ptsGood (B) · 63 of 100 points: Model quality 24.3/45, Memory fit 20.0/25, Speed 4.5/15, Memory use 15.0/15	CogVideoX 5BZhipu AI	`FP8`	9.6 GB	32.9 min	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 24.3/45, Memory fit 20.0/25, Speed 4.5/15, Memory use 15.0/15	CogVideoX 5B I2VZhipu AI	`FP8`	10.2 GB	32.9 min	Runs well
63 ptsGood (B) · 63 of 100 points: Model quality 24.8/45, Memory fit 20.0/25, Speed 3.7/15, Memory use 15.0/15	Wan 2.1 T2V 1.3BAlibaba	`FP16`	8.4 GB	48.7 min	Runs well

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.