Hardware · Android
What AI models can the Other Android device (4 GB RAM) run?
- RAM
- 4.0 GB
- One app can use
- 1.8 GB
- Memory bandwidth
- 34 GB/s
- FP16 compute
- 1.0 TFLOPS
- Released
- 2022
A model runs in RAM (the 4.0 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 1.8 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 | 45% (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 (4 GB RAM)
Android
Best LLMs for the Other Android device (4 GB RAM)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 53Fair quality (C) · 53 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. | LFM3 1.7B | Q4_K_M | 1.8 GB | 17.8 tok/s | Runs welltight fit |
| 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 0.9B | Q4_K_M | 1.3 GB | 32.1 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q4_K_M | 1.5 GB | 23.7 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | Q3_K_M | 1.6 GB | 20.7 tok/s | Runs welltight fit |
| 34Basic quality (D) · 34 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. | MiniCPM5 1B | Q4_K_M | 1.5 GB | 28.5 tok/s | Runs well |
| 33Basic quality (D) · 33 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. | MiniCPM-V 4.7 1B | Q3_K_M | 1.5 GB | 25.7 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | Q3_K_M | 1.3 GB | 34.0 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | Q4_K_M | 1.2 GB | 35.4 tok/s | Runs great |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | Q3_K_M | 1.6 GB | 21.2 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 1.2B | Q3_K_M | 1.3 GB | 34.0 tok/s | Runs great |
| 25Basic quality (D) · 25 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. | EXAONE 4.0 1.2B | Q3_K_M | 1.7 GB | 31.1 tok/s | Runs welltight fit |
| 23Basic quality (D) · 23 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. | Granite 4.0 H 1B | Q3_K_M | 1.4 GB | 27.3 tok/s | Runs well |
Best Image models for the Other Android device (4 GB RAM)
None of the image models in our catalog fit in this much memory.
Best Video models for the Other Android device (4 GB RAM)
None of the video models in our catalog fit in this much memory.
Best Decision models for the Other Android device (4 GB RAM)
None of the decision models in our catalog fit in this much memory.
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.