LLMap
Models /GLM 4.6V /Can I run it?
Compatibility check

Can I run GLM 4.6V on H100 80GB SXM?

Yes — it runs.best quant:
Decode speed
35 tok/sest
Usable context
33K
Memory
80 GB
Fits in memory35 tok/sest · 33K ctx
Spills to system RAMest
Too largeest
What is quantisation? →
GLM 4.6V
108B · full specs & benchmarks →
H100 80GB SXM
80 GB · everything it runs →