Published collection
COLIBRI runs GLM-5.2 on a 25GB machine with no GPU
This approach shows a feasible path for running ultra-large models at low speed on consumer hardware.
- Published entries
- 1
- Sources
- 1
- Date range
- 2026-08-12
- Primary labels
- Industry · 行业 · Compute/infrastructure · COLIBRI
Published evidence
Every entry keeps its summary and a path back to the source context.
COLIBRI runs GLM-5.2 on a 25GB machine with no GPU
COLIBRI runs GLM-5.2 on a 25GB, GPU-free machine by keeping active parameters in RAM and streaming the rest from disk on demand.
Original source