LLMap
Models /Phi 4 Multimodal Instruct /Can I run it?
Compatibility check

Can I run Phi 4 Multimodal Instruct on GeForce GTX 1660 SUPER?

Yes — it runs.best quant:
Decode speed
79 tok/sest
Usable context
4K
Memory
6 GB
Fits in memory79 tok/sest · 4K ctx
Spills to system RAMest
Spills to system RAMest
What is quantisation? →
Phi 4 Multimodal Instruct
5.6B · full specs & benchmarks →
GeForce GTX 1660 SUPER
6 GB · everything it runs →