LLMap
Models /Llama 4 Scout /Can I run it?
Compatibility check

Can I run Llama 4 Scout on Apple M3 Ultra (80-core GPU)?

Yes — it runs.best quant:
Decode speed
9 tok/sest
Usable context
262K
Memory
512 GB
Fits in memory9 tok/sest · 262K ctx
Fits in memory7 tok/sest · 262K ctx
Fits in memory5 tok/sest · 262K ctx
What is quantisation? →
Llama 4 Scout
109B · full specs & benchmarks →
Apple M3 Ultra (80-core GPU)
512 GB · everything it runs →