Can I run this LLM?
Can a Mac Studio M5 Ultra (256GB) run DeepSeek V4 Flash (MoE)?
DeepSeek · MIT · estimated for a 256.0 GB machine at 4K context.
Yes — it runs great.
Best fit: DeepSeek V4 Flash (MoE) at Q4_K_M · 155.1 GB · 70–105 tok/s on a Mac Studio M5 Ultra (256GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 96.8 GB | 89–133 tok/s | Runs great |
| Q3_K_M | 128.1 GB | 78–117 tok/s | Runs great |
| Q4_K_M | 155.1 GB | 70–105 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M5 Ultra (256GB) runsDeepSeek V4 Flash (MoE) on other machinesWhat to buy to run it →
Ran DeepSeek V4 Flash (MoE) on a Mac Studio M5 Ultra (256GB)? Add your real numbers →