Can OneJev 0.8B run on iPhone 17 Pro Max?
Estimated weights fit · custom workflow required
Weight fit is not phone app support
The tracked Q4_K_M weights are 0.7GB; the generic working-memory estimate is 1.4GB against 7.8GB usable. Image inputs need additional projector memory.
OneJev scores typed decisions in a single forward pass, not chat replies. The decode estimates below are not measured decision latency. The publisher's qev server and System One client are required; AICanRun has not verified a phone app route.
Not measured
decision latency
1.4GB
needed at Q4_K_M
Q4_K_M
quant checked
needs 1.4 GBusable 7.8 GB
Apple A19 Pro12 GB RAMMetal
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q4_K_M GGUF (0.7 GB) + mmap overhead | 0.7 |
| KV cache | 4K context window | 0.1 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q4_K_M, 4K context | 1.4 |
| Working budget | 12 GB RAM − iOS reserve (jetsam limit) | 7.8 |
| Headroom | remaining inside the working budget | 6.4 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q2_K | 0.5 GB | ✓ Runs great | ~69.1 tokens/s |
| IQ4_XS | 0.6 GB | ✓ Runs great | ~57.6 tokens/s |
| Q3_K_M | 0.6 GB | ✓ Runs great | ~57.6 tokens/s |
| Q4_K_S | 0.6 GB | ✓ Runs great | ~57.6 tokens/s |
| Q4_K_M BEST HERE | 0.7 GB | ✓ Runs great | ~49.4 tokens/s |
| Q5_K_M | 0.8 GB | ✓ Runs great | ~43.2 tokens/s |
| Q6_K | 0.8 GB | ✓ Runs great | ~43.2 tokens/s |
| Q8_0 | 1.1 GB | ✓ Runs great | ~31.4 tokens/s |
Use the right workflow for this model
The model fits in memory, but it is not an ordinary chat model.
This model is designed to return calibrated probabilities for typed choices from text or images. PocketPal does not provide the required the publisher's qev server and System One client; image inputs also need a vision projector, so the tracked file is not a beginner phone-chat path.
Read the publisher workflow ↗If you only want a normal private chat, use this simpler model instead:
Check Llama 3.2 3BRelated checks
More on iPhone 17 Pro Max
OneJev 0.8B on other phones