What AI models can the Samsung Galaxy S23 / S23+ run?

RAM: 8.0 GB
Storage: 128 GB – 512 GB
One app can use: 4.4 GB
Memory bandwidth: 67 GB/s
FP16 compute: 2.6 TFLOPS
Released: 2023

176 / 622 LLMs run Best: Nemotron Labs Dory 1.0 4B 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 Galaxy S23 / S23+ has 8 GB of RAM, whatever its storage (128 GB, 256 GB or 512 GB). A model runs in RAM (the 8.0 GB here), not in storage. Storage (128 GB, 256 GB or 512 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	Samsung
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 8 Gen 2 for Galaxy
RAM type	LPDDR5X
Versions sold	S23: 8 GB RAM with 128 GB, 256 GB or 512 GB S23+: 8 GB RAM with 256 GB or 512 GB
Bandwidth figure	67.2 GB/s, the chip’s rated memory speed (the phone maker publishes none)
Note	Adreno 740 GPU; 8 GB LPDDR5X-8400 (67.2 GB/s).

Apps that run models well on the Samsung Galaxy S23 / S23+

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 Samsung Galaxy S23 / S23+

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 78/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron Labs Dory 1.0 4BNVIDIA	`Q4_K_M`	3.5 GB	15.3 tok/s	Runs well
58Good quality (B) · 58 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.	Gemma 4 E2BGoogle	`Q4_K_M`	3.8 GB	26.4 tok/s	Runs welltight fit
62Good quality (B) · 62 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.	Spark-X2.6 4BSparkLLM	`Q4_K_M`	3.4 GB	14.8 tok/s	Runs well
57Good quality (B) · 57 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.	MiniCPM5 2BOpenBMB	`Q4_K_M`	2.5 GB	24.1 tok/s	Runs well
57Good quality (B) · 57 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.	TMax 4BAi2	`Q4_K_M`	3.4 GB	14.4 tok/s	Runs well
58Good quality (B) · 58 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.	Qwen3.5 4BAlibaba	`Q4_K_M`	3.7 GB	13.0 tok/s	Runs well
57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Nanbeige4.2 3BBOSS Zhipin (Nanbeige)	`Q3_K_M`	4.1 GB	18.8 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 74/100 (quality, fit, speed and memory use) sets the ranking.	Agents-A1 4BInternScience	`Q4_K_M`	3.6 GB	13.4 tok/s	Runs well
42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Unlimited OCR 2 (3B-A0.6B)Baidu	`Q5_K_M`	3.5 GB	64.7 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 73/100 (quality, fit, speed and memory use) sets the ranking.	Fara 1.5 4BMicrosoft	`Q4_K_M`	3.6 GB	13.4 tok/s	Runs well
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q2_K`	4.0 GB	61.9 tok/s	Runs welltight fit
38Basic quality (D) · 38 of 100: how capable the model is at Q5_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	`Q5_K_M`	3.5 GB	64.7 tok/s	Runs great

Best Image models for the Samsung Galaxy S23 / S23+

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

Best Video models for the Samsung Galaxy S23 / S23+

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

Best Decision models for the Samsung Galaxy S23 / S23+

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.