Can Yi 34B Chat 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-Chat-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Yi 34B Chat: RTX 5090 (32 GB, launch MSRP $1,999) at Q5_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the Mac M3 Ultra 256GB: Hy3 (299B, MoE) at Q4_K_M, about 173 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
Yi 34B Chat on every GPU and Mac · Every model that runs on the Mac M3 Ultra 256GB · 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 (01-ai/Yi-34B-Chat), Apple specs. Model data last checked 2026-11-18; refreshed hourly.