# Can I run DeepSeek-R1-Distill-Llama 8B on Apple M3 Ultra (256GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~6.4 GB of ~192 GB usable. You have room for FP16 for higher quality.

- Model: 8B, Q4_K_M 4.92 GB
- Device: 256 GB unified, ~192 GB usable for weights
- Needs ~6.4 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on macOS: LM Studio
- Command: `ollama run deepseek-r1:8b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/deepseek-r1, https://huggingface.co/bartowski/DeepSeek-R1-Distill-Llama-8B-GGUF, https://github.com/deepseek-ai/DeepSeek-R1.

More: https://localmodel.run/can-i-run/deepseek-r1-distill-llama-8b/apple-m3-ultra-256gb