Lossless compression cuts GLM-5.2 memory by 25%
hambandit · hn · 2026-07-20
A lossless compression experiment reports that GLM-5.2 can be stored in 25% less memory.
The post points to a write-up on weight compression and highlights the practical implication: same model, lower memory footprint, with no loss in weights/quality implied by the “lossless” framing.
More from Infra
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11
- Your p99 latency benchmark may be lying: a deep dive into coordinated omission — Franc0Fernand0 · 2026-09-11