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

Can I run Qwen2.5 72B Instruct on NVIDIA DGX Spark (GB10)?

Yes — it runs.best quant:
Decode speed
5 tok/sest
Usable context
33K
Memory
128 GB
Fits in memory5 tok/sest · 33K ctx
Fits in memory4 tok/sest · 33K ctx
Fits in memory3 tok/sest · 33K ctx
What is quantisation? →
Qwen2.5 72B Instruct
72.7B · full specs & benchmarks →
NVIDIA DGX Spark (GB10)
128 GB · everything it runs →