Compatibility check
Can I run Qwen2.5 VL 72B Instruct on H100 80GB SXM?
Yes — it runs.best quant: Q4_K_M
Decode speed
60 tok/sest
Usable context
66K
Memory
80 GB
Q4_K_MFits in memory60 tok/sest · 66K ctx
Q5_K_MFits in memory51 tok/sest · 66K ctx
Q8_0Spills to system RAMest
