Can Hy4 Preview run on the Mac M3 Ultra 256GB?
No. Even at 2-bit with 8K context, Hy4 Preview needs about 274 GB, more than the 192 GB usable on the Mac M3 Ultra 256GB.
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
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 273 GB No | 274 GB No | 276 GB No | 286 GB No | — |
| 3-bit (Q3_K_M) | 356 GB No | 356 GB No | 359 GB No | 369 GB No | — |
| 4-bit (Q4_K_M) | 445 GB No | 445 GB No | 448 GB No | 458 GB No | — |
| 5-bit (Q5_K_M) | 519 GB No | 519 GB No | 522 GB No | 532 GB No | — |
| 6-bit (Q6_K) | 597 GB No | 597 GB No | 600 GB No | 610 GB No | — |
| 8-bit (Q8_0) | 773 GB No | 773 GB No | 776 GB No | 786 GB No | — |
| 16-bit (F16/BF16) | 1454 GB No | 1454 GB No | 1457 GB No | 1467 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
Hardware that does fit it
What fits instead
- No listed GPU with a list price runs Hy4 Preview fully in memory. The smallest listed hardware that does is the Mac M3 Ultra 512GB (512 GB).
- Largest popular model that fits the Mac M3 Ultra 256GB: Hy3 (299B, MoE) at Q4_K_M, about 173 GB at 8K context.
"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 Preview 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-preview), Apple specs. Model data last checked 2026-11-17; refreshed hourly.