RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek V4 Flash run on the Mac M3 Ultra 256GB?

Yes. At 8K context the best fit is Q4_K_M, using about 167 GB of the 192 GB usable on the Mac M3 Ultra 256GB. Estimated speed ceiling: ~95 tokens/sec.

Newer compressed-attention design: long-context figures are an upper bound.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)103 GB Fits103 GB Fits105 GB Fits114 GB Fits155
3-bit (Q3_K_M)133 GB Fits134 GB Fits136 GB Fits145 GB Fits119
4-bit (Q4_K_M)167 GB Fits167 GB Fits169 GB Fits178 GB Tight95
5-bit (Q5_K_M)194 GB No194 GB No197 GB No206 GB No—
6-bit (Q6_K)223 GB No224 GB No226 GB No235 GB No—
8-bit (Q8_0)289 GB No289 GB No292 GB No301 GB No—
16-bit (F16/BF16)543 GB No543 GB No546 GB No555 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.

More

DeepSeek V4 Flash on every GPU and Mac · Every model that runs on the Mac M3 Ultra 256GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-V4-Flash), Apple specs. Data as of 2026-11-17.