Run GLM 5.2 with only 192 GB ram 🫰
Introducing a REAP50-Q3 quant by Pipe Network.
Reduced 50% in size by keeping half of the most-salient experts per layer.
Download on @huggingface: huggingface.co/pipenetwork/GL…
Introducing GLM-5.2: Frontier Intelligence, Open Weights
- Significant improvements in coding and agentic tasks
- Strong long-horizon capabilities with a 1M context window
- Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong
Ornith 397B is now available on Apple silicon 🫰
Specialized for agentic coding, this model features a self-improving training framework.
MLX quants by Pipe Network are live on @huggingface: huggingface.co/collections/pi…
Ornith 397B is now available on Apple silicon 🫰
Specialized for agentic coding, this model features a self-improving training framework.
MLX quants by Pipe Network are live on @huggingface: huggingface.co/collections/pi…
Aloha! 🌺 Meet Ornith-1.0, a family of open-source LLMs specialized for agentic coding.
Ornith-1.0 spans the full parameter sizes including 9B Dense, 31B Dense, 35B MoE, and 397B MoE. It achieves state-of-the-art performance among open-source models of comparable size on
Multiple flavors of GLM 5.2 are now live!
Run the size that fits your hardware:
• REAP50 - 381B params
• REAP37 - 472B params
• REAP25 - 562B params
Full Pipe Network collection on @huggingface: huggingface.co/collections/pi…
Run GLM 5.2 with only 192 GB ram 🫰
Introducing a REAP50-Q3 quant by Pipe Network.
Reduced 50% in size by keeping half of the most-salient experts per layer.
Download on @huggingface: huggingface.co/pipenetwork/GL…
Run GLM 5.2 with only 192 GB ram 🫰
Introducing a REAP50-Q3 quant by Pipe Network.
Reduced 50% in size by keeping half of the most-salient experts per layer.
Download on @huggingface: huggingface.co/pipenetwork/GL…