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

Compatibility check

Can I run Phi 4 Multimodal Instruct on Apple M1 Ultra (64-core GPU)?

Yes — it runs.best quant:

Decode speed

165 tok/sest

Usable context

131K

Memory

128 GB

Fits in memory165 tok/sest · 131K ctx

Fits in memory141 tok/sest · 131K ctx

Fits in memory94 tok/sest · 131K ctx

What is quantisation? →

Phi 4 Multimodal Instruct

5.6B · full specs & benchmarks →

Apple M1 Ultra (64-core GPU)

128 GB · everything it runs →