Can Step 3.7 Flash run on the Mac M3 Ultra 512GB?
Yes. At 8K context the best fit is Q8_0, using about 203 GB of the 384 GB usable on the Mac M3 Ultra 512GB. Estimated speed ceiling: ~4 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 73.0 GB Fits | 74.5 GB Fits | 83.5 GB Fits | 120 GB Fits | 11 |
| 3-bit (Q3_K_M) • | 90.1 GB Fits | 91.6 GB Fits | 101 GB Fits | 137 GB Fits | 9 |
| 4-bit (Q4_K_M) | 117 GB Fits | 119 GB Fits | 128 GB Fits | 164 GB Fits | 7 |
| 5-bit (Q5_K_M) | 136 GB Fits | 138 GB Fits | 147 GB Fits | 183 GB Fits | 6 |
| 6-bit (Q6_K) | 156 GB Fits | 158 GB Fits | 167 GB Fits | 203 GB Fits | 5 |
| 8-bit (Q8_0) • | 201 GB Fits | 203 GB Fits | 212 GB Fits | 248 GB Fits | 4 |
| 16-bit (F16/BF16) • | 376 GB Tight | 378 GB Tight | 387 GB No | 423 GB No | 2 |
• real GGUF file size from stepfun-ai/Step-3.7-Flash-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Step 3.7 Flash: DGX Spark (128 GB, launch MSRP $3,999) at Q3_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the Mac M3 Ultra 512GB: GLM 5.3 Flash (321B, MoE) at Q8_0, about 318 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
Step 3.7 Flash 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 (stepfun-ai/Step-3.7-Flash), Apple specs. Model data last checked 2026-11-17; refreshed hourly.