Can Yi 34B run on the Mac M3 Ultra 256GB?
Yes. At 8K context the best fit is F16, using about 66.5 GB of the 192 GB usable on the Mac M3 Ultra 256GB. Estimated speed ceiling: ~12 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 15.0 GB Fits | 56 |
| 3-bit (Q3_K_M) • | 17.0 GB Fits | 49 |
| 4-bit (Q4_K_M) • | 20.7 GB Fits | 40 |
| 5-bit (Q5_K_M) • | 24.1 GB Fits | 34 |
| 6-bit (Q6_K) • | 27.7 GB Fits | 29 |
| 8-bit (Q8_0) • | 35.5 GB Fits | 22 |
| 16-bit (F16/BF16) | 65.5 GB Fits | 12 |
• real GGUF file size from TheBloke/Yi-34B-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
More
Yi 34B 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 (01-ai/Yi-34B), Apple specs. Data as of 2026-11-17.