OpenWeightsTerminal

GLM 5.3 Flash

GLM 5.3 Flash

2× RTX PRO 6000 · EXL3 · TensorFold 0.6.5

Decode · tok/s
238
Prefill
—
tok/100W
39.7
2x RTX PRO 6000 (300 W per GPU): 238 tok/s on prose, single stream

Kurcide print, quoted by Mia. Rank is the quoted 238 prose one-stream.

Officialclaimed
Open pair