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.
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
Data: Hugging Face Hub (stepfun-ai/Step-3.7-Flash), Apple specs. Model data last checked 2026-11-17; refreshed hourly.