# Best local LLMs for Nvidia GeForce RTX 4080 (16GB)

Updated: 2026-06-15

Nvidia GeForce RTX 4080 (16GB): 16 GB vram, ~15 GB usable. Runs 45 of 67 tracked models.

- gpt-oss 20B (21B): runs
- DeepSeek-V2-Lite (16B): runs
- Phi-4 14B (14B): runs
- Qwen2.5 14B (14B): runs
- Qwen3 14B (14B): runs
- DeepSeek-R1-Distill-Qwen 14B (14B): runs
- Qwen2.5 Coder 14B (14B): runs
- Mistral Nemo 12B (12.2B): runs
- Gemma 3 12B (12B): runs
- Llama 3.2 Vision 11B (10.7B): runs
- Falcon3 10B (10B): runs
- Gemma 2 9B (9B): runs

More: https://localmodel.run/best-llm-for/nvidia-rtx-4080-16gb