Qwen3.8-Flash-Next
Qwen's 180B mixture-of-experts with 512 experts. Only a few billion parameters are active per token – that is what makes it fast.
Parameters: 180B (MoE, 4-bit + MTP) · Memory: 74.7 GB · Context: 256K
| Model | Chip | Generation | Reading | First token | Power while answering |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next 180B · 4-bit + MTP · 74.7 GB | Mac Studio M5 Ultra 96 GB | 80 tok/s | 3,270 tok/s | 0.12 s | 38 W |
| Mac mini M6 16 GB | does not fit | ||||
Qwen3.8-Flash-Next does not fit into 16 GB of memory. (Mac mini M6)
Last measured: November 10, 2026
Free: 2 chat questions and 2 minutes with your coding agent. No card needed.
M5 Ultra vs. Mac mini M6Does the model fit on my Mac?Rent a Mac Studio M5 Ultra by the hourOpenAI- and Anthropic-compatible API on a Mac Studio M5 UltraTry a Mac Studio M5 Ultra before you buy oneOrnith-1.5 122BOrnith-1.5 9B