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

Compatibility check

Can I run Phi 4 Multimodal Instruct on Apple M2 (10-core GPU)?

Yes — it runs.best quant:

Decode speed

21 tok/sest

Usable context

66K

Memory

24 GB

Fits in memory21 tok/sest · 66K ctx

Fits in memory18 tok/sest · 66K ctx

Fits in memory12 tok/sest · 66K ctx

What is quantisation? →

Phi 4 Multimodal Instruct

5.6B · full specs & benchmarks →

Apple M2 (10-core GPU)

24 GB · everything it runs →