Can Kimi Dev 72B run on the Mac M3 Ultra 512GB?
Yes. At 8K context the best fit is F16, using about 139 GB of the 384 GB usable on the Mac M3 Ultra 512GB. Estimated speed ceiling: ~6 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) | 27.3 GB Fits | 28.6 GB Fits | 36.1 GB Fits | 66.1 GB Fits | 30 |
| 3-bit (Q3_K_M) • | 37.0 GB Fits | 38.3 GB Fits | 45.8 GB Fits | 75.8 GB Fits | 22 |
| 4-bit (Q4_K_M) | 43.3 GB Fits | 44.6 GB Fits | 52.1 GB Fits | 82.1 GB Fits | 18 |
| 5-bit (Q5_K_M) | 50.2 GB Fits | 51.4 GB Fits | 58.9 GB Fits | 88.9 GB Fits | 16 |
| 6-bit (Q6_K) • | 61.9 GB Fits | 63.1 GB Fits | 70.6 GB Fits | 101 GB Fits | 13 |
| 8-bit (Q8_0) • | 73.9 GB Fits | 75.1 GB Fits | 82.6 GB Fits | 113 GB Fits | 11 |
| 16-bit (F16/BF16) • | 137 GB Fits | 139 GB Fits | 146 GB Fits | 176 GB Fits | 6 |
• real GGUF file size from unsloth/Kimi-Dev-72B-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
More
Kimi Dev 72B 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 (moonshotai/Kimi-Dev-72B), Apple specs. Data as of 2026-11-17.