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

Compatibility check

Can I run Phi 4 Multimodal Instruct on Apple M1 (8-core GPU)?

Yes — it runs.best quant:

Decode speed

14 tok/sest

Usable context

33K

Memory

16 GB

Fits in memory14 tok/sest · 33K ctx

Fits in memory12 tok/sest · 33K ctx

Fits in memory8 tok/sest · 33K ctx

What is quantisation? →

Phi 4 Multimodal Instruct

5.6B · full specs & benchmarks →

Apple M1 (8-core GPU)

16 GB · everything it runs →