# Can I run Qwen3 4B on 8GB RAM Laptop (CPU/iGPU only)?

> **Yes, it runs.** Runs at Q4_K_M using ~3.8 GB of ~5 GB usable.

Last validated: 2026-06-15.

## Memory math
- Qwen3 4B: 4B; Q4_K_M weighs 2.5 GB on disk.
- At Q4_K_M with a 4k context it needs ~3.8 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- 8GB RAM Laptop (CPU/iGPU only): 8 GB ram, ~5 GB usable for model weights.
- Headroom: ~1.2 GB.

## How to run
Recommended quant: Q4_K_M. Best tool on Windows: LM Studio.

```sh
ollama run qwen3:4b
```

## Run Qwen3 4B on other devices
- [Apple M1 (8GB)](https://localmodel.run/can-i-run/qwen3-4b/apple-m1-8gb)
- [iPhone 15 Pro](https://localmodel.run/can-i-run/qwen3-4b/iphone-15-pro)
- [iPhone 16](https://localmodel.run/can-i-run/qwen3-4b/iphone-16)
- [iPhone 16 Pro](https://localmodel.run/can-i-run/qwen3-4b/iphone-16-pro)
- [Generic Android Phone (8GB RAM)](https://localmodel.run/can-i-run/qwen3-4b/android-generic-8gb)
- [iPhone 17](https://localmodel.run/can-i-run/qwen3-4b/iphone-17)

## Other models that run on 8GB RAM Laptop (CPU/iGPU only)
- [Gemma 3 4B (4B)](https://localmodel.run/can-i-run/gemma-3-4b/laptop-8gb)
- [Phi-3.5-mini 3.8B (3.82B)](https://localmodel.run/can-i-run/phi-3.5-mini/laptop-8gb)
- [Phi-4-mini 3.8B (3.8B)](https://localmodel.run/can-i-run/phi-4-mini-3.8b/laptop-8gb)
- [Qwen2.5-VL 3B (3.75B)](https://localmodel.run/can-i-run/qwen2.5-vl-3b/laptop-8gb)
- [Qwen2.5 3B (3.09B)](https://localmodel.run/can-i-run/qwen2.5-3b/laptop-8gb)
- [Qwen2.5 Coder 3B (3.09B)](https://localmodel.run/can-i-run/qwen2.5-coder-3b/laptop-8gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/qwen3:4b, https://huggingface.co/Qwen/Qwen3-4B-GGUF, https://github.com/QwenLM/Qwen3.
More: https://localmodel.run/can-i-run/qwen3-4b/laptop-8gb