Log inSign up
Pipe Network
1,642 posts
Image
user avatar
Pipe Network
@pipenetwork
Pipe Network AI Labs
pipe.network
Joined April 2022
14
Following
179.6K
Followers
  • Pinned
    user avatar
    Pipe Network
    @pipenetwork
    Jun 18
    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…
    Image
    Image
    user avatar
    Z.ai
    @Zai_org
    Jun 16
    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
    37K
  • user avatar
    Pipe Network
    @pipenetwork
    3h
    Anybody want MLX for the smaller 9B and 35B Ornith?
    user avatar
    Pipe Network
    @pipenetwork
    Jun 26
    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…
    Image
    00:00
    3K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 26
    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…
    Image
    00:00
    Image
    user avatar
    Ornith
    @ornith_
    Jun 25
    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
    100K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 25
    ⏳
    Image
    2.9K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 24
    By age 30, everyone should have: 1. Dual monitors 2. Gym subscription 3. Back pain 4. @NVIDIAAI DGX Station running GLM 5.2
    3.6K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 23
    What's your favorite local model? One reply wins $500 in credits and early access 👇
    Image
    3.4K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 22
    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…
    Image
    3.7K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 21
    Automatic routing to the best model for the job. Who's building this? 😏
    1.6K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 20
    What hardware do you wish to use GLM 5.2 on? Taking requests 👇
    user avatar
    Pipe Network
    @pipenetwork
    Jun 18
    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…
    Image
    2.5K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 19
    How many toks/sec did you get in 1996?
    Image
    1.2K
  • Pipe Network reposted
    user avatar
    0xSero
    @0xSero
    Jun 19
    2x RTX pro 6000 and 2x spark might be able to run this
    user avatar
    Pipe Network
    @pipenetwork
    Jun 18
    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…
    Image
    15K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 18
    Replying to @pipenetwork
    Quantized to Q3_K_M (~169 GB), you can run it with llama.cpp on: - Mac Studio with 192GB+ unified memory - 2× RTX Pro 6000 - 6× RTX 5090 - 8× RTX 3090
    1.4K
  • user avatar
    Pipe Network
    @pipenetwork
    Jun 18
    Fifty one near-lossless models available for download from Pipe. What are you building today?
    Image
    pipenetwork (Pipenetwork)
    From huggingface.co
    769

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
Advertisement
Advertisement