Can deepseek moe 16b base run on the Mac M3 Ultra 256GB?
Yes. At 8K context the best fit is F16, using about 32.8 GB of the 192 GB usable on the Mac M3 Ultra 256GB. Estimated speed ceiling: ~145 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 7.7 GB Fits | 707 |
| 3-bit (Q3_K_M) • | 9.4 GB Fits | 559 |
| 4-bit (Q4_K_M) • | 11.6 GB Fits | 437 |
| 5-bit (Q5_K_M) • | 13.0 GB Fits | 383 |
| 6-bit (Q6_K) • | 15.1 GB Fits | 323 |
| 8-bit (Q8_0) • | 17.7 GB Fits | 272 |
| 16-bit (F16/BF16) | 32.0 GB Fits | 145 |
• real GGUF file size from mradermacher/deepseek-moe-16b-base-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
More
deepseek moe 16b base on every GPU and Mac · Every model that runs on the Mac M3 Ultra 256GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/deepseek-moe-16b-base), Apple specs. Data as of 2026-11-17.