GLM-5.3-SLIM GGUF quantization trends on Hugging Face for llama.cpp
Scantist · hf · 2026-11-08
A GGUF quantization of GLM-5.3-SLIM published by Scantist is trending on Hugging Face. Tagged for llama.cpp local deployment, it lists a glmmoedsa MoE architecture with NAS-related tags and supports English and Chinese text generation — a ready-made quant for running the latest GLM MoE model locally.
More from Infra
- Anthropic API users beware: cache 5-minute window can make bundled credits hilariously wasteful — teortaxesTex · 2026-11-08
- Harbor turns one: 200T tokens/week, 10M+ Terminal-Bench runs, 1B+ rollouts — BenBlaiszik · 2026-11-08
- LLM-leaderboard-style atlas benchmarks silicon photonics foundries on component specs — jwt0625 · 2026-11-08
- GPU ran 16s→11s per image after cooling fix: thermal throttling unlocked — elittle1234 · 2026-11-08
- Nadella on datacenter water use: closed-loop cooling equals one restaurant's yearly usage — pbaylies · 2026-11-08
- Jane Street Is 'a Commune with GPUs,' Says SemiAnalysis Founder Dylan Patel — dylan522p · 2026-11-08