Models /Phi 4 Multimodal Instruct /Can I run it?

Compatibility check

Can I run Phi 4 Multimodal Instruct on Apple M5 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

127 tok/sest

Usable context

131K

Memory

128 GB

Fits in memory127 tok/sest · 131K ctx

Fits in memory108 tok/sest · 131K ctx

Fits in memory72 tok/sest · 131K ctx

What is quantisation? →

Phi 4 Multimodal Instruct

5.6B · full specs & benchmarks →

Apple M5 Max (40-core GPU)

128 GB · everything it runs →