# Can I run Phi-4 14B on Nvidia GeForce RTX 3090 (24GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~10.8 GB of ~23 GB usable. You have room for Q8_0 for higher quality.

- Model: 14B, Q4_K_M 9.05 GB
- Device: 24 GB vram, ~23 GB usable for weights
- Needs ~10.8 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on Windows: LM Studio
- Command: `ollama run phi4:14b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/phi4, https://ollama.com/library/phi4/tags, https://huggingface.co/bartowski/phi-4-GGUF, https://lmarena.ai/leaderboard.

More: https://localmodel.run/can-i-run/phi-4-14b/nvidia-rtx-3090-24gb