What AI models can the Apple iPhone SE (2nd generation) run?

RAM: 3.0 GB
Storage: 64 GB – 256 GB
One app can use: 1.4 GB
Memory bandwidth: 34 GB/s
FP16 compute: 0.8 TFLOPS
Released: 2020

33 / 622 LLMs run Best: PaddleOCR-VL 1.6 0.9B 0 / 61 Image models run None fit 0 / 43 Video models run None fit 0 / 70 Decision models run No iOS app

Every iPhone SE (2nd generation) has 3 GB of RAM, whatever its storage (64 GB, 128 GB or 256 GB). A model runs in RAM (the 3.0 GB here), not in storage. Storage (64 GB, 128 GB or 256 GB on this version) only keeps the downloaded files, and even the smallest size has room for several. iOS lets one app hold only part of the RAM before it closes the app, so we plan around 1.4 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	Mobile device (system on a chip)
App share of memory	45% (what one app can typically hold before the system closes it)
Chip	Apple A13
RAM type	3 GB LPDDR4X-4266 (teardown)
Versions sold	SE (2nd generation): 3 GB RAM with 64 GB, 128 GB or 256 GB
Bandwidth figure	34.1 GB/s, from teardowns (the maker publishes no memory speed)
Note	A13 with a 4-core GPU; 3 GB LPDDR4X-4266 (34.1 GB/s).
Maker’s specifications	www.apple.com

Apps that run models well on the Apple iPhone SE (2nd generation)

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 iPhone SE (2nd generation)

Quality	Model	Quant	Memory	Speed	Runs
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	PaddleOCR-VL 1.6 0.9BBaidu	`Q4_K_M`	1.3 GB	44.8 tok/s	Runs welltight fit
35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM-OCR 1.0 1.3BOpenBMB	`Q3_K_M`	1.3 GB	42.8 tok/s	Runs welltight fit
30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM5 1BOpenBMB	`Q3_K_M`	1.3 GB	51.5 tok/s	Runs welltight fit
28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM-V 4.7 1BOpenBMB	`Q2_K`	1.3 GB	45.6 tok/s	Runs welltight fit
26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	LFM2.5 1.2B InstructLiquid AI	`Q3_K_M`	1.3 GB	47.5 tok/s	Runs welltight fit
25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 0.8BAlibaba	`Q5_K_M`	1.3 GB	40.9 tok/s	Runs welltight fit
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	LFM2 1.2BLiquid AI	`Q3_K_M`	1.3 GB	47.5 tok/s	Runs welltight fit
19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	Granite 4.0 H 1BIBM	`Q2_K`	1.3 GB	48.4 tok/s	Runs welltight fit
16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 3 1BGoogle	`Q3_K_M`	1.1 GB	55.6 tok/s	Runs great
17Basic quality (D) · 17 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	LFM2 700MLiquid AI	`Q6_K`	1.3 GB	40.3 tok/s	Runs welltight fit
16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	LFM2-VL 1.6BLiquid AI	`Q2_K`	1.3 GB	44.7 tok/s	Runs welltight fit
14Basic quality (D) · 14 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	surya ocr 2.5Datalab	`Q4_K_M`	1.1 GB	62.4 tok/s	Runs great

Best Image models for the Apple iPhone SE (2nd generation)

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

Best Video models for the Apple iPhone SE (2nd generation)

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

Best Decision models for the Apple iPhone SE (2nd generation)

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.