# Can I run SmolLM2 360M on 32GB RAM Laptop (CPU/iGPU only)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~1.2 GB of ~28 GB usable. You have room for FP16 for higher quality.

- Model: 0.362B, Q4_K_M 0.271 GB
- Device: 32 GB ram, ~28 GB usable for weights
- Needs ~1.2 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on Windows: LM Studio
- Command: `ollama run smollm2:360m`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/smollm2:360m, https://huggingface.co/bartowski/SmolLM2-360M-Instruct-GGUF, https://venturebeat.com/ai/ai-on-your-smartphone-hugging-faces-smollm2-brings-powerful-models-to-the-palm-of-your-hand.

More: https://localmodel.run/can-i-run/smollm2-360m/laptop-32gb