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

Can I run Qwen2.5 72B Instruct on Instinct MI300X?

Yes — it runs.best quant:
Decode speed
78 tok/sest
Usable context
33K
Memory
192 GB
Fits in memory78 tok/sest · 33K ctx
Fits in memory67 tok/sest · 33K ctx
Fits in memory45 tok/sest · 33K ctx
What is quantisation? →
Qwen2.5 72B Instruct
72.7B · full specs & benchmarks →
Instinct MI300X
192 GB · everything it runs →