Models /GLM 4.7 Flash /Can I run it?

Compatibility check

Can I run GLM 4.7 Flash on RTX PRO 6000 Blackwell?

Yes — it runs.best quant:

Decode speed

64 tok/sest

Usable context

131K

Memory

96 GB

Fits in memory64 tok/sest · 131K ctx

Fits in memory55 tok/sest · 131K ctx

Fits in memory37 tok/sest · 131K ctx

Fits in memory20 tok/sest · 66K ctx

What is quantisation? →

31.2B · full specs & benchmarks →

RTX PRO 6000 Blackwell

96 GB · everything it runs →