OLMo · 7B · Desktop / import
OLMo 3 7B Instruct on a phone
Allen AI’s fully open 7B instruct model — a transparent alternative to Llama/Qwen.
- Parameters
- 7B
- Typical Q4
- ~4.3 GB (Q4)
- RAM to budget
- ~6.6 GB
- Engines
- GGUF
Get it running
allenai/Olmo-3-7B-Instruct (2025). Community GGUF. Hugging Face: allenai/Olmo-3-7B-Instruct.
Load in LM Studio or Ollama, then chat from the phone.
Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.
Phones that can run it
- iPhone 17 Pro Max Fits
- iPhone 17 Pro Fits
- Pixel 10 Pro XL Runs well
- Pixel 10 Pro Runs well
- Pixel 9 Pro XL Runs well
- Pixel 9 Pro Runs well
- OnePlus 13 Runs well
- OnePlus 12 Runs well
- Xiaomi 15 Runs well
- ASUS ROG Phone 9 Runs well
Tight (close other apps)
- iPhone Air Tight
- Pixel 10 Tight
- Galaxy S26 Ultra Tight
- Pixel 9 Tight
- Galaxy S25 Ultra Tight
- Galaxy S25 Tight
- Galaxy S24 Ultra Tight
- Xiaomi 14 Tight
- Nothing Phone (3) Tight