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

Can DeepSeek R1 0528 run on the DGX Spark?

No. Even at 2-bit with 8K context, DeepSeek R1 0528 needs about 229 GB, more than the 109 GB usable on the DGX Spark.

On this machine the GPU and CPU share one memory pool, so CPU offload does not add room. A smaller quant, a shorter context or more memory are the options.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •229 GB No229 GB No231 GB No237 GB No—
3-bit (Q3_K_M) •299 GB No299 GB No301 GB No307 GB No—
4-bit (Q4_K_M) •378 GB No378 GB No380 GB No386 GB No—
5-bit (Q5_K_M) •444 GB No444 GB No446 GB No452 GB No—
6-bit (Q6_K) •514 GB No514 GB No516 GB No522 GB No—
8-bit (Q8_0) •665 GB No665 GB No667 GB No674 GB No—
16-bit (F16/BF16) •1251 GB No1251 GB No1253 GB No1259 GB No—

• real GGUF file size from unsloth/DeepSeek-R1-0528-GGUF. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M3 Ultra 512GB

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 DGX Spark · Other models that fit 64 GB VRAM · 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), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.