What AI models can the Apple iPad Pro 11-inch / 13-inch (M4) (8 GB RAM) run?

RAM: 8.0 GB
Storage: 256 GB – 512 GB
One app can use: 4.4 GB
Memory bandwidth: 120 GB/s
FP16 compute: 4.3 TFLOPS
Released: 2024

175 / 621 LLMs run Best: Nemotron Labs Dory 1.0 4B 7 / 61 Image models run Best: SDXL Turbo 0 / 43 Video models run None fit 0 / 70 Decision models run No iOS app

A model runs in RAM (the 8.0 GB here), not in storage. Storage (256 GB or 512 GB 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 4.4 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	55% (what one app can typically hold before the system closes it)
Chip	Apple M4
RAM type	8 GB or 16 GB unified memory (Apple)
Versions sold	11-inch and 13-inch: 8 GB RAM with 256 GB or 512 GB 11-inch and 13-inch: 16 GB RAM with 1 TB or 2 TB
Bandwidth figure	120.0 GB/s, as the maker states it
Note	M4 (9-core GPU with 8 GB, 10-core with 16 GB on 1/2 TB models); LPDDR5X-7500 (120 GB/s).
Maker’s specifications	www.apple.com

Apps that run models well on the Apple iPad Pro 11-inch / 13-inch (M4) (8 GB RAM)

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 Pro 11-inch / 13-inch (M4) (8 GB RAM)

Quality	Model	Quant	Memory	Speed	Runs
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.	Nemotron Labs Dory 1.0 4BNVIDIA	`Q4_K_M`	3.5 GB	38.0 tok/s	Runs great
62Good quality (B) · 62 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.	Spark-X2.6 4BSparkLLM	`Q4_K_M`	3.4 GB	36.8 tok/s	Runs great
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM5 2BOpenBMB	`Q6_K`	3.0 GB	41.7 tok/s	Runs great
60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E2BGoogle	`Q5_K_M`	4.3 GB	54.4 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.	TMax 4BAi2	`Q4_K_M`	3.4 GB	36.0 tok/s	Runs great
58Good quality (B) · 58 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 4BAlibaba	`Q4_K_M`	3.7 GB	32.5 tok/s	Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Nanbeige4.2 3BBOSS Zhipin (Nanbeige)	`Q3_K_M`	4.1 GB	46.9 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 79/100 (quality, fit, speed and memory use) sets the ranking.	Agents-A1 4BInternScience	`Q4_K_M`	3.6 GB	33.3 tok/s	Runs great
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	LFM3 1.7BLiquid AI	`Q8_0`	2.5 GB	44.6 tok/s	Runs great
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Fara 1.5 4BMicrosoft	`Q4_K_M`	3.6 GB	33.3 tok/s	Runs great
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 4B Thinking 2507Alibaba	`Q4_K_M`	4.3 GB	37.7 tok/s	Runs welltight fit
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	Granite 4.2 3BIBM	`Q4_K_M`	3.5 GB	41.4 tok/s	Runs great

Best Image models for the Apple iPad Pro 11-inch / 13-inch (M4) (8 GB RAM)

Quality	Model	Quant	Memory	Speed	Runs
39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	SDXL TurboStability AI	`FP8`	4.2 GB	2.4 s	Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	Realistic Vision V5.1SG161222	`FP16`	2.8 GB	21 s	Runs well
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	LCM DreamShaper v7Tsinghua (LCM)	`FP16`	2.8 GB	4.4 s	Runs great
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	DreamShaper 8Lykon	`FP16`	2.8 GB	21 s	Runs well
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	SD TurboStability AI	`FP16`	3.3 GB	1.4 s	Runs great
50Fair quality (C) · 50 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.	PixArt-Σ XL 1024PixArt	`FP16`	3.3 GB	27 s	Runs wellencoder unloaded after use

Best Video models for the Apple iPad Pro 11-inch / 13-inch (M4) (8 GB RAM)

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

Best Decision models for the Apple iPad Pro 11-inch / 13-inch (M4) (8 GB RAM)

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.