Hardware · Apple Silicon

What AI models can the Apple M2 (24 GB) run?

Unified memory: 24.0 GB
Usable for models: 16.1 GB
Memory bandwidth: 100 GB/s
FP16 compute: 3.6 TFLOPS
Released: 2022

455 / 621 LLMs run Best: Gemma 4 26B-A4B 55 / 61 Image models run Best: FLUX.2 [klein] 4B 17 / 43 Video models run Best: LTX-Video 2B 66 / 70 Decision models run Best: GLiNER2.5 Decide

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 24.0 GB.

More about this hardware

Maker	Apple Silicon
Type	Apple silicon (system on a chip)
Chip	Apple M2

Apps that run models well on the Apple M2 (24 GB)

macOS

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

4 products with the Apple M2 (24 GB)

MacBook Air (M2, 2022)Apple · Laptop · 8, 16 or 24 GB · $1,199–$1,599Product page (opens in a new tab)
MacBook Air (15-inch, M2, 2023)Apple · Laptop · 8, 16 or 24 GB · $1,299–$1,699Product page (opens in a new tab)
MacBook Pro (13-inch, M2, 2022)Apple · Laptop · 8, 16 or 24 GB · $1,299–$1,699Product page (opens in a new tab)
Mac mini (2023) (M2 or M2 Pro)Apple · Mini PC · 8, 16, 24 or 32 GB · $599–$1,699Product page (opens in a new tab)

Best LLMs for the Apple M2 (24 GB)

Quality	Model	Quant	Memory	Speed	Runs
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 26B-A4BGoogle	`Q3_K_M`	14.9 GB	32.2 tok/s	Runs welltight fit
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Raon-1 mini Preview (30B-A4B)KRAFTON	`Q3_K_M`	16.1 GB	28.8 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Maple Preview (20B-A1B)DeepGrove	`Q4_K_M`	14.3 GB	57.3 tok/s	Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	gpt-oss 20BOpenAI	`MXFP4`	14.0 GB	28.4 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q4_K_M`	9.4 GB	37.0 tok/s	Runs great
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	KAT-Coder V2.5 Dev (35B-A3B)Kuaishou	`Q2_K`	15.9 GB	49.0 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE 4.5 21B-A3B ThinkingBaidu	`Q4_K_M`	15.7 GB	31.5 tok/s	Runs welltight fit
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	LFM2.5 24B-A2BLiquid AI	`Q3_K_M`	13.8 GB	47.2 tok/s	Runs welltight fit
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GLM-4.7 Flash (30B-A3B)Zhipu AI	`Q2_K`	14.8 GB	49.0 tok/s	Runs welltight fit
65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	DiffusionGemma 26B-A4B ITGoogle	`Q3_K_M`	14.9 GB	30.8 tok/s	Runs welltight fit
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Qwen AgentWorld 35B-A3BAlibaba	`Q2_K`	15.9 GB	49.0 tok/s	Runs welltight fit
59Good quality (B) · 59 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Hunyuan Hy-Memory 30B-A3BTencent	`Q2_K`	14.7 GB	49.0 tok/s	Runs welltight fit

Best Image models for the Apple M2 (24 GB)

Quality	Model	Quant	Memory	Speed	Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	10.2 GB	18 s	Runs well
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`FP8`	12.4 GB	1.7 min	Slow
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`FP8`	12.6 GB	45 s	Slow
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-Image TurboBaidu	`FP8`	14.5 GB	57 s	Slowtight fit
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`FP8`	11.7 GB	34 s	Runs wellencoder unloaded after use
81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Z-ImageAlibaba (Tongyi)	`Q8 GGUF`	13.0 GB	6.5 min	Very slow

Best Video models for the Apple M2 (24 GB)

Quality	Model	Quant	Memory	Speed	Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	10.8 GB	7.5 min	Runs well
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 T2V 1.3BAlibaba	`FP8`	12.8 GB	71.7 min	Very slow
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI	`FP16`	14.7 GB	1.8 h	Very slowtight fit · encoder unloaded after use
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Bernini-R A14B (video generation + editing)ByteDance	`FP8`	10.7 GB	4.7 h	Very slowCPU offload
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP8`	11.0 GB	17.9 min	Slow

Best Decision models for the Apple M2 (24 GB)

Quality	Model	Quant	Memory	Speed	Runs
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	GLiNER2.5 DecideFastino	`F16`	1.7 GB	74 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`Q8_0`	2.8 GB	153 ms	Runs well
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	FRIDA-DecisionsSber AI	`Q8_0`	1.7 GB	106 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`Q8_0`	2.8 GB	153 ms	Runs well
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 86MMeta	`F16`	1.2 GB	84 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GLiClass ModernBERT Large v3Knowledgator	`F16`	1.5 GB	61 ms	Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 0.6BAlibaba	`Q8_0`	2.8 GB	153 ms	Runs well
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	OpenAI Privacy FilterOpenAI	`F16`	3.8 GB	11 ms	Runs great

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.