Hardware · Apple Silicon

What AI models can the Apple M2 (8 GB) run?

Unified memory: 8.0 GB
Usable for models: 5.4 GB
Memory bandwidth: 100 GB/s
FP16 compute: 3.6 TFLOPS
Released: 2022

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 8.0 GB.

Specifications

Maker	Apple Silicon
Type	Apple silicon (system on a chip)
Chip	Apple M2
Unified memory	8.0 GB
Usable for AI models	5.4 GB
Memory bandwidth	100 GB/s
FP16 compute	3.6 TFLOPS
Interface	UNIFIED
Released	2022

4 products with the Apple M2 (8 GB)

MacBook Air (M2, 2022)Apple · Laptop · 8, 16 or 24 GB · from $1,199Maker’s page (opens in a new tab)
MacBook Air (15-inch, M2, 2023)Apple · Laptop · 8, 16 or 24 GB · from $1,299Maker’s page (opens in a new tab)
MacBook Pro (13-inch, M2, 2022)Apple · Laptop · 8, 16 or 24 GB · from $1,299Maker’s page (opens in a new tab)
Mac mini (2023) (M2 or M2 Pro)Apple · Mini PC · 8, 16, 24 or 32 GB · from $599Maker’s page (opens in a new tab)

Best LLMs for the Apple M2 (8 GB)

Grade · points	Model	Quant	Memory	Speed	Fit
77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 15.0/15	TMax 4BAi2	`Q4_K_M`	3.9 GB	25.1 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 15.0/15	Qwen3.5 4BAlibaba	`Q4_K_M`	4.1 GB	22.7 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 15.0/15	Gemma 4 E2BGoogle	`Q4_K_M`	4.2 GB	20.6 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 15.0/15	Agents-A1 4BInternScience	`Q4_K_M`	4.1 GB	23.3 tok/s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 22.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q3_K_M`	5.1 GB	52.6 tok/s	Tight fit
76 ptsGreat (A) · 76 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 15.0/15	Fara 1.5 4BMicrosoft	`Q4_K_M`	4.1 GB	23.3 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 23.9/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15	Qwen3 4B Thinking 2507Alibaba	`Q4_K_M`	4.7 GB	26.3 tok/s	Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 12.7/15, Memory use 15.0/15	Granite 4.2 3BIBM	`Q4_K_M`	3.9 GB	28.9 tok/s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 9.8/15, Memory use 15.0/15	Gemma 4 E4BGoogle	`Q3_K_M`	5.1 GB	17.1 tok/s	Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 23.1/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15	Qwen3 4B Instruct 2507Alibaba	`Q4_K_M`	4.7 GB	26.3 tok/s	Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 23.9/45, Memory fit 24.0/25, Speed 11.2/15, Memory use 15.0/15	Mage-VL 4.7BMicrosoft	`Q4_K_M`	5.1 GB	22.3 tok/s	Tight fit
73 ptsGreat (A) · 73 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	North Micro VisionCohere	`Q4_K_M`	3.5 GB	42.6 tok/s	Runs well

Best Image models for the Apple M2 (8 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
75 ptsGreat (A) · 75 of 100 points: Model quality 32.6/45, Memory fit 18.0/25, Speed 9.5/15, Memory use 15.0/15	FLUX.2 [klein] 4BBlack Forest Labs	`Q4 GGUF`	4.6 GB	25 s	Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 17.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	SDXL TurboStability AI	`FP8`	4.2 GB	2.7 s	Runs well
70 ptsGood (B) · 70 of 100 points: Model quality 37.0/45, Memory fit 12.0/25, Speed 6.2/15, Memory use 15.0/15	Z-Image TurboAlibaba (Tongyi)	`FP8`	4.4 GB	58 s	Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 23.8/45, Memory fit 18.0/25, Speed 13.1/15, Memory use 15.0/15	SDXL-Lightning (4-step)ByteDance	`FP8`	4.7 GB	13 s	Tight fit
68 ptsGood (B) · 68 of 100 points: Model quality 35.2/45, Memory fit 12.0/25, Speed 6.3/15, Memory use 15.0/15	FLUX.2 [klein] 9BBlack Forest Labs	`Q4 GGUF`	4.3 GB	56 s	Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 25.6/45, Memory fit 18.0/25, Speed 9.6/15, Memory use 15.0/15	DreamShaper XL v2 TurboLykon	`FP8`	4.7 GB	24 s	Tight fit

Best Video models for the Apple M2 (8 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
63 ptsGood (B) · 63 of 100 points: Model quality 15.8/45, Memory fit 23.0/25, Speed 10.1/15, Memory use 15.0/15	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	4.7 GB	6.6 min	Tight fit
57 ptsUsable (C) · 57 of 100 points: Model quality 22.1/45, Memory fit 12.0/25, Speed 8.3/15, Memory use 15.0/15	LTX-Video 2BLightricks	`FP8`	4.0 GB	9.7 min	Runs well
50 ptsUsable (C) · 50 of 100 points: Model quality 19.8/45, Memory fit 10.0/25, Speed 5.4/15, Memory use 15.0/15	CogVideoX 2BZhipu AI	`FP8`	4.7 GB	23.3 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.