Hardware · Google
What AI models can the Google Pixel 7 / 7a run?
- RAM
- 8.0 GB
- Storage
- 128 GB – 256 GB
- One app can use
- 4.4 GB
- Memory bandwidth
- 51 GB/s
- FP16 compute
- 1.4 TFLOPS
- Released
- 2022
Every Pixel 7 / 7a 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 | |
|---|---|
| Type | Mobile device (system on a chip) |
| App share of memory | 55% (what one app can typically hold before the system closes it) |
| Chip | Tensor G2 |
| RAM type | 8 GB LPDDR5 (Google) |
| Versions sold | 7: 8 GB RAM with 128 GB or 256 GB 7a: 8 GB RAM with 128 GB |
| Bandwidth figure | 51.2 GB/s, the chip’s rated memory speed (the phone maker publishes none) |
| Note | Tensor G2 (Mali-G710 MP7 GPU); 8 GB LPDDR5 (51.2 GB/s). |
| Maker’s specifications | support.google.com |
Apps that run models well on the Google Pixel 7 / 7a
Android
Best LLMs for the Google Pixel 7 / 7a
| 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 77/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q4_K_M | 3.5 GB | 11.6 tok/s | Runs well |
| 62Good quality (B) · 62 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. | Spark-X2.6 4B | Q4_K_M | 3.4 GB | 11.3 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 76/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q4_K_M | 3.8 GB | 20.1 tok/s | Runs welltight fit |
| 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) | Q5_K_M | 3.5 GB | 52.1 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 73/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | Q4_K_M | 3.4 GB | 11.0 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 73/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q4_K_M | 2.5 GB | 18.4 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 73/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q3_K_M | 4.1 GB | 14.3 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 73/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | Q4_K_M | 3.6 GB | 10.2 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q2_K | 4.0 GB | 49.4 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) | Q5_K_M | 3.5 GB | 52.1 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 72/100 (quality, fit, speed and memory use) sets the ranking. | Fara 1.5 4B | Q4_K_M | 3.6 GB | 10.2 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q3_K_M | 3.2 GB | 12.8 tok/s | Runs well |
Best Image models for the Google Pixel 7 / 7a
None of the image models in our catalog fit in this much memory.
Best Video models for the Google Pixel 7 / 7a
None of the video models in our catalog fit in this much memory.
Best Decision models for the Google Pixel 7 / 7a
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.