Compatibility check
Can I run Qwen3 Next 80B A3B Instruct on Apple M2 Max (38-core GPU)?
Yes — it runs.best quant:
Decode speed
131 tok/sest
Usable context
131K
Memory
96 GB
Fits in memory131 tok/sest · 131K ctx
Fits in memory112 tok/sest · 66K ctx
Spills to system RAM
