Compatibility check
Can I run GLM 4.7 Flash on Radeon RX 7900 XT?
Partially — with CPU offload.best quant:
19 GB of weights, plus 2.6 GB for the software that runs it and the smallest conversation it can hold, comes to 21.6 GB against the 18.8 GB this 20 GB device leaves free.
Decode speed
—
Usable context
—
Memory
20 GB
Spills to system RAM
Spills to system RAM
Too large
Too large
Plan B — rent it
GLM 4.7 Flash is hosted by 5 providers from $0.40 per 1M output tokens (DeepInfra).Compare providers →
