Can MiniMax M2.5 run on the Mac M3 Ultra 512GB?
Yes. At 8K context the best fit is Q8_0, using about 229 GB of the 384 GB usable on the Mac M3 Ultra 512GB. Estimated speed ceiling: ~70 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) | 81.6 GB Fits | 82.6 GB Fits | 88.4 GB Fits | 112 GB Fits | 198 |
| 3-bit (Q3_K_M) | 106 GB Fits | 107 GB Fits | 113 GB Fits | 136 GB Fits | 152 |
| 4-bit (Q4_K_M) • | 131 GB Fits | 132 GB Fits | 137 GB Fits | 161 GB Fits | 123 |
| 5-bit (Q5_K_M) | 154 GB Fits | 154 GB Fits | 160 GB Fits | 184 GB Fits | 104 |
| 6-bit (Q6_K) • | 177 GB Fits | 178 GB Fits | 183 GB Fits | 207 GB Fits | 90 |
| 8-bit (Q8_0) • | 228 GB Fits | 229 GB Fits | 235 GB Fits | 258 GB Fits | 70 |
| 16-bit (F16/BF16) | 428 GB No | 429 GB No | 434 GB No | 458 GB No | — |
• real GGUF file size from lmstudio-community/MiniMax-M2.5-GGUF. Speed is a bandwidth ceiling (819 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs MiniMax M2.5: DGX Spark (128 GB, launch MSRP $3,999) at Q2_K, fully in VRAM at 8K context.
- Largest popular model that fits the Mac M3 Ultra 512GB: Nex N2.6 (321B, MoE) at Q8_0, about 319 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
MiniMax M2.5 on every GPU and Mac · Every model that runs on the Mac M3 Ultra 512GB · 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 (MiniMaxAI/MiniMax-M2.5), Apple specs. Model data last checked 2026-11-18; refreshed hourly.