# Can I run DeepSeek-R1-Distill-Qwen 14B on Nvidia GeForce RTX 4090 (24GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~10.7 GB of ~23 GB usable. You have room for Q8_0 for higher quality.

- Model: 14B, Q4_K_M 8.99 GB
- Device: 24 GB vram, ~23 GB usable for weights
- Needs ~10.7 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on Windows: LM Studio
- Command: `ollama run deepseek-r1:14b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/deepseek-r1, https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF, https://github.com/deepseek-ai/DeepSeek-R1.

More: https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-14b/nvidia-rtx-4090-24gb