Can OneJev 4B run on Motorola Razr+ (2026)?

Estimated weights fit · custom workflow required

Weight fit is not phone app support

The tracked Q4_K_M weights are 3.1GB; the generic working-memory estimate is 4.1GB against 9GB 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
4.1GB
needed at Q4_K_M
Q4_K_M
quant checked
needs 4.1 GBusable 9 GB
Snapdragon 8s Gen 312 GB RAMCPU / GPU

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (3.1 GB) + mmap overhead3.3
KV cache4K context window0.3
Runtimellama.cpp + app overhead0.6
Total neededat Q4_K_M, 4K context4.1
Working budget12 GB RAM − Android system reserve9
Headroomremaining inside the working budget4.9

Pick your quant

QuantDownloadVerdictSpeed
Q2_K 2.1 GB✓ Runs great~14.4 tokens/s
Q3_K_M 2.5 GB✓ Runs great~12.1 tokens/s
IQ4_XS 2.9 GB✓ Runs great~10.4 tokens/s
Q4_K_S 2.9 GB✓ Runs great~10.4 tokens/s
Q4_K_M BEST HERE3.1 GB✓ Runs great~9.8 tokens/s
Q5_K_M 3.5 GB✓ Runs great~8.6 tokens/s
Q6_K 4 GB! Runs, barely~7.6 tokens/s
Q8_0 5.2 GB! Runs, barely~5.8 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 3B

Related checks

More on Motorola Razr+ (2026)
Qwen3 0.6BQwen3 1.7BLlama 3.2 1BLlama 3.2 3BGemma 3 1B
OneJev 4B on other phones
Xiaomi 18 FoldOPPO Find X8 Provivo X200 ProGalaxy S26Galaxy S26+