What AI models can the Nothing Phone (4b) run?

RAM: 8.0 GB
Storage: 128 GB – 256 GB
One app can use: 4.4 GB
Memory bandwidth: 34 GB/s
FP16 compute: 0.9 TFLOPS
Released: 2026

176 / 622 LLMs run Best: Gemma 4 E2B 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 Nothing Phone (4b) has 8 GB of RAM, whatever its storage (128 GB or 256 GB). A model runs in RAM (the 8.0 GB here), not in storage. Storage (128 GB or 256 GB 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 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	Nothing
Type	Mobile device (system on a chip)
App share of memory	55% (what one app can typically hold before the system closes it)
Chip	Snapdragon 6 Gen 4
RAM type	8 GB LPDDR4X
Versions sold	Phone (4b): 8 GB RAM with 128 GB or 256 GB
Bandwidth figure	34.1 GB/s, the chip’s rated memory speed (the phone maker publishes none)
Note	Snapdragon 6 Gen 4; 8 GB LPDDR4X (34.1 GB/s).
Maker’s specifications	intl.nothing.tech

Apps that run models well on the Nothing Phone (4b)

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 Nothing Phone (4b)

Quality	Model	Quant	Memory	Speed	Runs
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E2BGoogle	`Q4_K_M`	3.8 GB	13.4 tok/s	Runs welltight fit
41Fair quality (C) · 41 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.	Unlimited OCR 2 (3B-A0.6B)Baidu	`Q4_K_M`	3.1 GB	43.8 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 73/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron Labs Dory 1.0 4BNVIDIA	`Q3_K_M`	3.0 GB	10.0 tok/s	Runs well
38Basic quality (D) · 38 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.	Unlimited OCR (3B-A0.6B)Baidu	`Q4_K_M`	3.1 GB	43.8 tok/s	Runs great
57Good quality (B) · 57 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.	MiniCPM5 2BOpenBMB	`Q4_K_M`	2.5 GB	12.2 tok/s	Runs well
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q2_K`	4.0 GB	34.7 tok/s	Runs welltight fit
36Basic quality (D) · 36 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.	Granite 4.0 H Tiny (7B-A1B)IBM	`Q3_K_M`	4.1 GB	35.3 tok/s	Runs welltight fit
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	`Q2_K`	3.9 GB	11.2 tok/s	Runs welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	Nanbeige4.2 3BBOSS Zhipin (Nanbeige)	`Q2_K`	3.7 GB	12.1 tok/s	Runs welltight fit
36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	LFM2.5 8B-A1BLiquid AI	`Q2_K`	4.1 GB	30.5 tok/s	Runs welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E4BGoogle	`Q2_K`	3.9 GB	11.2 tok/s	Runs welltight fit
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	LFM3 1.7BLiquid AI	`Q4_K_M`	1.8 GB	17.8 tok/s	Runs well

Best Image models for the Nothing Phone (4b)

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

Best Video models for the Nothing Phone (4b)

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

Best Decision models for the Nothing Phone (4b)

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.