Models /GLM 4.5 /Can I run it?

Compatibility check

Can I run GLM 4.5 on B200 (SXM 192GB)?

Partially — with CPU offload.best quant:

Decode speed

—

Usable context

—

Memory

192 GB

Spills to system RAM

Spills to system RAMest

Too large

What is quantisation? →

Plan B — rent it

GLM 4.5 is hosted by 3 providers from $2.20 per 1M output tokens (Novita AI).Compare providers →

358B / 32B · full specs & benchmarks →

B200 (SXM 192GB)

192 GB · everything it runs →