What AI models can the Apple iPad Air 11-inch / 13-inch (M4) run?

RAM: 12.0 GB
Storage: 128 GB – 1 TB
One app can use: 7.2 GB
Memory bandwidth: 120 GB/s
FP16 compute: 3.9 TFLOPS
Released: 2026

292 / 621 LLMs run Best: Nemotron 3.5 Bolt E4B 29 / 61 Image models run Best: FLUX.2 [klein] 4B 3 / 43 Video models run Best: LTX-Video 2B 0 / 70 Decision models run No iOS app

Every iPad Air 11-inch / 13-inch (M4) has 12 GB of RAM, whatever its storage (128 GB, 256 GB, 512 GB or 1 TB). A model runs in RAM (the 12.0 GB here), not in storage. Storage (128 GB, 256 GB, 512 GB or 1 TB on this version) only keeps the downloaded files, and even the smallest size has room for several. iPadOS lets one app hold only part of the RAM before it closes the app, so we plan around 7.2 GB; a model bigger than that won’t run. Phone apps such as PocketPal AI download a model once, then run it with no connection.

More about this hardware

Maker	Apple
Type	Tablet (system on a chip)
App share of memory	60% (what one app can typically hold before the system closes it)
Chip	Apple M4 (9-core GPU)
RAM type	12 GB unified memory (Apple)
Versions sold	11-inch and 13-inch: 12 GB RAM with 128 GB, 256 GB, 512 GB or 1 TB
Bandwidth figure	120.0 GB/s, as the maker states it
Note	M4 with an 8-core CPU and 9-core GPU; 12 GB unified memory at 120 GB/s, as Apple states.
Maker’s specifications	www.apple.com

Apps that run models well on the Apple iPad Air 11-inch / 13-inch (M4)

iOS

PocketPal AIRuns the model on the device itself, offline: download it once in the app.

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

Best LLMs for the Apple iPad Air 11-inch / 13-inch (M4)

Quality	Model	Quant	Memory	Speed	Runs
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.	Nemotron 3.5 Bolt E4BNVIDIA	`Q4_K_M`	5.6 GB	33.6 tok/s	Runs great
64Good quality (B) · 64 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.	Nanbeige4.2 3BBOSS Zhipin (Nanbeige)	`Q4_K_M`	4.6 GB	36.3 tok/s	Runs great
64Good quality (B) · 64 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.	Gemma 4 E4BGoogle	`Q4_K_M`	5.6 GB	33.6 tok/s	Runs great
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E2BGoogle	`Q6_K`	4.9 GB	45.7 tok/s	Runs great
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	MiMo V2.6 Distill Qwen 9BXiaomi	`Q4_K_M`	6.6 GB	16.1 tok/s	Runs welltight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	SenseNova Loop 9B PreviewSenseTime	`Q4_K_M`	7.0 GB	15.7 tok/s	Runs welltight fit
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.5 9BDeepReinforce	`Q4_K_M`	6.8 GB	15.7 tok/s	Runs welltight fit
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 9BAlibaba	`Q4_K_M`	6.8 GB	15.7 tok/s	Runs welltight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q4_K_M`	5.6 GB	83.7 tok/s	Runs great
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q3_K_M`	6.7 GB	62.4 tok/s	Runs welltight fit
71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.0 9BDeepReinforce	`Q4_K_M`	6.8 GB	15.7 tok/s	Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	TMax 9BAi2	`Q4_K_M`	6.3 GB	16.9 tok/s	Runs welltight fit

Best Image models for the Apple iPad Air 11-inch / 13-inch (M4)

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 78/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	6.2 GB	18 s	Runs welltight fit · encoder unloaded after use
52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	SDXL-Lightning (4-step)ByteDance	`FP8`	5.6 GB	12 s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`Q4 GGUF`	5.7 GB	2.2 min	Very slowencoder unloaded after use
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`Q4 GGUF`	6.1 GB	59 s	Slowencoder unloaded after use
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	DreamShaper XL v2 TurboLykon	`FP8`	5.6 GB	22 s	Runs well
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	Juggernaut XL v9RunDiffusion	`FP8`	5.6 GB	76 s	Slow

Best Video models for the Apple iPad Air 11-inch / 13-inch (M4)

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 66/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	6.1 GB	7.4 min	Runs wellencoder unloaded after use
35Basic quality (D) · 35 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.	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	4.7 GB	6.3 min	Runs well
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP8`	6.2 GB	17.7 min	Slowtight fit · encoder unloaded after use

Best Decision models for the Apple iPad Air 11-inch / 13-inch (M4)

None of the decision models in our catalog fit in this much memory.

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.