What AI models can the Google Pixel 9 Pro / 9 Pro XL / 9 Pro Fold run?

RAM: 16.0 GB
Storage: 128 GB – 1 TB
One app can use: 9.9 GB
Memory bandwidth: 68 GB/s
FP16 compute: 1.5 TFLOPS
Released: 2024

342 / 622 LLMs run Best: Mellum2.1 Thinking (12B-A2.5B) 0 / 61 Image models run No Android app 0 / 43 Video models run No Android app 0 / 70 Decision models run No Android app

Every Pixel 9 Pro / 9 Pro XL / 9 Pro Fold has 16 GB of RAM, whatever its storage (128 GB, 256 GB, 512 GB or 1 TB). A model runs in RAM (the 16.0 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. Android 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	Google
Type	Mobile device (system on a chip)
App share of memory	62% (what one app can typically hold before the system closes it)
Chip	Tensor G4
RAM type	LPDDR5X
Versions sold	9 Pro: 16 GB RAM with 128 GB, 256 GB, 512 GB or 1 TB 9 Pro XL: 16 GB RAM with 128 GB, 256 GB, 512 GB or 1 TB 9 Pro Fold: 16 GB RAM with 256 GB or 512 GB
Bandwidth figure	68.3 GB/s, the chip’s rated memory speed (the phone maker publishes none)
Note	Tensor G4 (Mali-G715 MC7 GPU); 16 GB LPDDR5X (68.3 GB/s).
Maker’s specifications	support.google.com

Apps that run models well on the Google Pixel 9 Pro / 9 Pro XL / 9 Pro Fold

Android

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 Google Pixel 9 Pro / 9 Pro XL / 9 Pro Fold

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 81/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q4_K_M`	8.1 GB	22.8 tok/s	Runs well
80Great quality (A) · 80 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 12BGoogle	`Q5_K_M`	9.8 GB	4.3 tok/s	Slowtight fit
57Good quality (B) · 57 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.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q4_K_M`	5.6 GB	40.9 tok/s	Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	`Q4_K_M`	5.6 GB	13.7 tok/s	Runs well
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Maple Preview (20B-A1B)DeepGrove	`Q2_K`	8.8 GB	56.1 tok/s	Runs welltight fit
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E4BGoogle	`Q4_K_M`	5.6 GB	13.7 tok/s	Runs well
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	LFM2.5 8B-A1BLiquid AI	`Q4_K_M`	5.9 GB	36.1 tok/s	Runs great
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE 4.5 21B-A3B ThinkingBaidu	`Q2_K`	9.8 GB	30.6 tok/s	Runs welltight fit
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Nanbeige4.2 3BBOSS Zhipin (Nanbeige)	`Q4_K_M`	4.6 GB	14.8 tok/s	Runs well
43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI)	`Q3_K_M`	8.9 GB	48.1 tok/s	Runs welltight fit
50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Kimi-VL A3B Thinking 2506Moonshot AI	`Q3_K_M`	8.9 GB	24.5 tok/s	Runs welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E2BGoogle	`Q4_K_M`	3.8 GB	26.8 tok/s	Runs well

Best Image models for the Google Pixel 9 Pro / 9 Pro XL / 9 Pro Fold

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

Best Video models for the Google Pixel 9 Pro / 9 Pro XL / 9 Pro Fold

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

Best Decision models for the Google Pixel 9 Pro / 9 Pro XL / 9 Pro Fold

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.