LLMap
Models /Qwen2.5 7B Instruct /Can I run it?
Compatibility check

Can I run Qwen2.5 7B Instruct on Instinct MI300X?

Yes — it runs.best quant:
Decode speed
748 tok/sest
Usable context
33K
Memory
192 GB
Fits in memory748 tok/sest · 33K ctx
Fits in memory637 tok/sest · 33K ctx
Fits in memory427 tok/sest · 33K ctx
What is quantisation? →
Qwen2.5 7B Instruct
7.6B · full specs & benchmarks →
Instinct MI300X
192 GB · everything it runs →