# Can I run DeepSeek V3 on Nvidia GeForce RTX 4060 Ti (16GB)?

Updated: 2026-06-15

**No, not enough memory.** Needs ~383.7 GB even at Q4_K_M, but only ~15 GB is usable.

- Model: 671B (MoE, 37B active), Q4_K_M 376.66 GB
- Device: 16 GB vram, ~15 GB usable for weights
- Needs ~383.7 GB at Q4_K_M; recommended quant: n/a
- Best tool on Windows: LM Studio
- Command: `ollama run deepseek-v3:671b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/deepseek-v3, https://ollama.com/library/deepseek-v3/tags, https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF, https://huggingface.co/deepseek-ai/DeepSeek-V3-0324.

More: https://localmodel.run/can-i-run/deepseek-v3/nvidia-rtx-4060-ti-16gb