RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can DeepSeek R1 0528 run on the Mac M3 Ultra 512GB?

Yes. At 8K context the best fit is Q3_K_M, using about 288 GB of the 384 GB usable on the Mac M3 Ultra 512GB. Estimated speed ceiling: ~45 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •222 GB Fits223 GB Fits224 GB Fits231 GB Fits59
3-bit (Q3_K_M) •288 GB Fits288 GB Fits290 GB Fits296 GB Fits45
4-bit (Q4_K_M) •382 GB Tight382 GB Tight384 GB Tight390 GB No34
5-bit (Q5_K_M) •446 GB No447 GB No448 GB No455 GB No—
6-bit (Q6_K) •515 GB No516 GB No517 GB No524 GB No—
8-bit (Q8_0) •665 GB No665 GB No667 GB No674 GB No—
16-bit (F16/BF16)1276 GB No1276 GB No1278 GB No1284 GB No—

• real GGUF file size from bartowski/deepseek-ai_DeepSeek-R1-0528-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

DeepSeek R1 0528 on every GPU and Mac · Every model that runs on the Mac M3 Ultra 512GB · Apple Silicon guide · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (deepseek-ai/DeepSeek-R1-0528), Apple specs. Model data last checked 2026-11-18; refreshed hourly.