# Can I run SmolLM2 1.7B on Nvidia GeForce RTX 4070 (12GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~2.2 GB of ~11 GB usable. You have room for FP16 for higher quality.

- Model: 1.7B, Q4_K_M 1.06 GB
- Device: 12 GB vram, ~11 GB usable for weights
- Needs ~2.2 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on Windows: LM Studio
- Command: `ollama run smollm2:1.7b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/smollm2, https://huggingface.co/bartowski/SmolLM2-1.7B-Instruct-GGUF, https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF, https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B, https://lmarena.ai/leaderboard.

More: https://localmodel.run/can-i-run/smollm2-1.7b/nvidia-rtx-4070-12gb