nodes

#nodes

@AlpinDale: GLM-5.2-FP8 running on 4 nodes of 4090-48GBs at around 28 tok/s decode. The nodes have an interconnect speed of 10 giga…

X AI KOLs Following ↗ · 3d ago Cached

AlpinDale reports running GLM-5.2-FP8 on 4 nodes of RTX 4090 (48GB) achieving ~28 tok/s decode over 10Gbit ethernet, with plans to optimize using DSpark.

0 favorites 0 likes

nodes

@AlpinDale: GLM-5.2-FP8 running on 4 nodes of 4090-48GBs at around 28 tok/s decode. The nodes have an interconnect speed of 10 giga…

Submit Feedback