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

Can Hy4 Flash run on the Mac M3 Ultra 256GB?

Yes. At 8K context the best fit is Q6_K, using about 169 GB of the 192 GB usable on the Mac M3 Ultra 256GB.

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)77.6 GB Fits77.7 GB Fits78.1 GB Fits79.6 GB Fits—
3-bit (Q3_K_M)101 GB Fits101 GB Fits101 GB Fits103 GB Fits—
4-bit (Q4_K_M)126 GB Fits126 GB Fits127 GB Fits128 GB Fits—
5-bit (Q5_K_M)147 GB Fits147 GB Fits147 GB Fits149 GB Fits—
6-bit (Q6_K)169 GB Fits169 GB Fits169 GB Fits171 GB Fits—
8-bit (Q8_0)219 GB No219 GB No219 GB No221 GB No—
16-bit (F16/BF16)411 GB No411 GB No411 GB No413 GB No—

• real GGUF file size. 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

Hy4 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

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 (tencent/Hy4-flash), Apple specs. Model data last checked 2026-11-18; refreshed hourly.