Colibri: Run 744B-parameter GLM-5.2 MoE model on consumer hardware with 25GB RAM using pure C
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦 - JustVugg/colibri
Read the full articleYou might also wanna read
Researchers Serve 229B-Parameter MoE Model Across Five Consumer GPUs Over Public Internet
We serve MiniMax-M2.5, a 229B-parameter mixture-of-experts model, split across five consumer RTX 5090s in five European countries. The stage
prime-rl 0.6.0 Enables Trillion-Parameter MoE Model Training on Agentic Workloads
prime-rl 0.6.0 trains trillion-parameter MoE models on heavy agentic workloads at the highest efficiency. A deep dive into the inference and
prime-rl 0.6.0 Enables Trillion-Parameter MoE Model Training on Agentic Workloads
prime-rl 0.6.0 trains trillion-parameter MoE models on heavy agentic workloads at the highest efficiency. A deep dive into the inference and
LongCat-Flash: Meituan's 560B-Parameter MoE Language Model with Dynamic Computation and Open-Source Release
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and a
GLM 5.2 Open-Weight Model Beats Claude Code on IDOR Detection Benchmark at Lower Cost
Among models given nothing but a prompt, the best open-weight option beat Claude Opus 4.8.
GLM-5.2: Running Z.ai's 744B-Parameter Open Model Locally with Unsloth Dynamic GGUFs
Run the new GLM-5.2 model by Z.ai on local hardware!
GLM-5.2: Running Z.ai's 744B-Parameter Open Model Locally with Unsloth Dynamic GGUFs
Run the new GLM-5.2 model by Z.ai on local hardware!
GLM 5.2 - API Pricing & Benchmarks
GLM 5.2 is a large-scale reasoning model from Z.ai. $0.95 per million input tokens, $3 per million output tokens. 1,048,576 token context wi

Comments
Sign in to join the conversation.
No comments yet. Be the first.