# Can I run Granite 3.1 2B on Nvidia GeForce RTX 4080 (16GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~2.8 GB of ~15 GB usable. You have room for FP16 for higher quality.

- Model: 2.53B, Q4_K_M 1.55 GB
- Device: 16 GB vram, ~15 GB usable for weights
- Needs ~2.8 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on Windows: LM Studio
- Command: `ollama run granite3.1-dense:2b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/granite3.1-dense:2b, https://huggingface.co/bartowski/granite-3.1-2b-instruct-GGUF, https://community.ibm.com/community/user/blogs/nickolus-plowden/2025/01/12/granite-31-delivers-powerful-performance-longer-co, https://huggingface.co/ibm-granite/granite-3.1-2b-instruct.

More: https://localmodel.run/can-i-run/granite-3.1-2b/nvidia-rtx-4080-16gb