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

Can I run Phi 4 Multimodal Instruct on H100 80GB SXM?

Yes — it runs.best quant:
Decode speed
789 tok/sest
Usable context
131K
Memory
80 GB
Fits in memory789 tok/sest · 131K ctx
Fits in memory673 tok/sest · 131K ctx
Fits in memory450 tok/sest · 131K ctx
What is quantisation? →
Phi 4 Multimodal Instruct
5.6B · full specs & benchmarks →
H100 80GB SXM
80 GB · everything it runs →