What AI models can the Other iPad (16 GB RAM) run?

RAM: 16.0 GB
One app can use: 9.9 GB
Memory bandwidth: 100 GB/s
FP16 compute: 3.5 TFLOPS
Released: 2024

341 / 621 LLMs run Best: Mellum2.1 Thinking (12B-A2.5B) 41 / 61 Image models run Best: FLUX.2 [klein] 4B 6 / 43 Video models run Best: LTX-Video 2B 0 / 70 Decision models run No iOS app

A model runs in RAM (the 16.0 GB here), not in storage. Storage 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 9.9 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	62% (what one app can typically hold before the system closes it)
Chip	Apple Apple silicon
Bandwidth figure	100.0 GB/s, estimated, see the note below

Apps that run models well on the Other iPad (16 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 Other iPad (16 GB RAM)

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 84/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q4_K_M`	8.1 GB	43.1 tok/s	Runs great
76Great quality (A) · 76 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.	K2 Horizon 7BInstitute of Foundation Models	`Q4_K_M`	7.3 GB	14.0 tok/s	Runs well
78Great quality (A) · 78 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 12BGoogle	`Q4_K_M`	8.6 GB	10.5 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 82/100 (quality, fit, speed and memory use) sets the ranking.	MiMo V2.6 Distill Qwen 9BXiaomi	`Q4_K_M`	6.6 GB	13.4 tok/s	Runs well
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	13.1 tok/s	Runs well
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.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q6_K`	7.3 GB	54.2 tok/s	Runs great
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	13.1 tok/s	Runs well
72Great quality (A) · 72 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.	Qwen3.5 9BAlibaba	`Q4_K_M`	6.8 GB	13.1 tok/s	Runs well
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	13.1 tok/s	Runs well
66Good quality (B) · 66 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.	Nemotron 3.5 Bolt E4BNVIDIA	`Q4_K_M`	5.6 GB	28.0 tok/s	Runs well
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	14.1 tok/s	Runs well
64Good quality (B) · 64 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.	Gemma 4 E4BGoogle	`Q4_K_M`	5.6 GB	28.0 tok/s	Runs well

Best Image models for the Other iPad (16 GB RAM)

Quality	Model	Quant	Memory	Speed	Runs
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`Q4 GGUF`	8.6 GB	24 s	Runs welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`FP8`	7.9 GB	1.8 min	Slowencoder unloaded after use
78Great quality (A) · 78 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.2 [klein] 9BBlack Forest Labs	`Q4 GGUF`	8.0 GB	46 s	Slowencoder unloaded after use
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`FP8`	8.5 GB	48 s	Slowtight fit · encoder unloaded after use
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-Image TurboBaidu	`Q4 GGUF`	7.4 GB	82 s	Slowencoder unloaded after use
52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	SDXL-Lightning (4-step)ByteDance	`FP8`	5.6 GB	13 s	Runs great

Best Video models for the Other iPad (16 GB RAM)

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 65/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	6.1 GB	8.0 min	Runs wellencoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 T2V 1.3BAlibaba	`FP8`	7.1 GB	76.9 min	Very slowencoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 VACE 1.3BAlibaba	`FP8`	8.0 GB	83.3 min	Very slowencoder unloaded after use
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	4.7 GB	6.8 min	Runs well
45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP16`	7.9 GB	21.4 min	Slowencoder unloaded after use

Best Decision models for the Other iPad (16 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.