LLMap
Models /Qwen2.5 72B Instruct /Can I run it?
Compatibility check

Can I run Qwen2.5 72B Instruct on H100 80GB SXM?

Yes — it runs.best quant:
Decode speed
61 tok/sest
Usable context
33K
Memory
80 GB
Fits in memory61 tok/sest · 33K ctx
Fits in memory52 tok/sest · 33K ctx
Spills to system RAMest
What is quantisation? →
Qwen2.5 72B Instruct
72.7B · full specs & benchmarks →
H100 80GB SXM
80 GB · everything it runs →