What AI models can the Other Android device (12 GB RAM) run?

RAM: 12.0 GB
One app can use: 7.2 GB
Memory bandwidth: 34 GB/s
FP16 compute: 1.0 TFLOPS
Released: 2022

292 / 621 LLMs run Best: Ling 3.0 Tiny (8B-A1.3B) 0 / 61 Image models run No Android app 0 / 43 Video models run No Android app 0 / 70 Decision models run No Android app

A model runs in RAM (the 12.0 GB here), not in storage. Storage 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 7.2 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	Android
Type	Mobile device (system on a chip)
App share of memory	60% (what one app can typically hold before the system closes it)
Chip	Mid-range Android chip
Bandwidth figure	34.1 GB/s, estimated, see the note below

Apps that run models well on the Other Android device (12 GB RAM)

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 Other Android device (12 GB RAM)

Quality	Model	Quant	Memory	Speed	Runs
57Good quality (B) · 57 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.	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q4_K_M`	5.6 GB	22.0 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 76/100 (quality, fit, speed and memory use) sets the ranking.	MiMo V2.6 Distill Qwen 9BXiaomi	`Q4_K_M`	6.6 GB	3.3 tok/s	Slowtight fit
74Great quality (A) · 74 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.	SenseNova Loop 9B PreviewSenseTime	`Q4_K_M`	7.0 GB	3.2 tok/s	Slowtight fit
73Great quality (A) · 73 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.	Ornith 1.5 9BDeepReinforce	`Q4_K_M`	6.8 GB	3.2 tok/s	Slowtight fit
72Great quality (A) · 72 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 9BAlibaba	`Q4_K_M`	6.8 GB	3.2 tok/s	Slowtight fit
71Great quality (A) · 71 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.	Ornith 1.0 9BDeepReinforce	`Q4_K_M`	6.8 GB	3.2 tok/s	Slowtight fit
70Great quality (A) · 70 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 9BAi2	`Q4_K_M`	6.3 GB	3.4 tok/s	Slowtight fit
69Good quality (B) · 69 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.	Gemma 4 12BGoogle	`Q3_K_M`	7.1 GB	3.3 tok/s	Slowtight fit
58Good quality (B) · 58 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.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q3_K_M`	6.7 GB	15.2 tok/s	Runs welltight fit
67Good quality (B) · 67 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.	K2 Horizon 7BInstitute of Foundation Models	`Q3_K_M`	6.2 GB	4.4 tok/s	Slowtight fit
66Good quality (B) · 66 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.	UI-Mate 9BTencent	`Q4_K_M`	6.6 GB	3.3 tok/s	Slowtight fit
66Good quality (B) · 66 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.	UI-Venus 2 9BAnt Group (inclusionAI)	`Q4_K_M`	6.6 GB	3.3 tok/s	Slowtight fit

Best Image models for the Other Android device (12 GB RAM)

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

Best Video models for the Other Android device (12 GB RAM)

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

Best Decision models for the Other Android device (12 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.