Shapelearn Qwen 3.8 27B (13.1 GB VRAM)

2 comments

• _ache_ 58 minutes ago
  From my own test. It's not faster than the unsloth model.

  Disclarer: I'm unsing Vulkan on an AMD GC.
• sheo 49 minutes ago
  Aged like milk

  https://news.ycombinator.com/item?id=49746618

  [-]
  • Mashimo 13 minutes ago
    In the comments it reads like bonsei falls apart on longer running tasks.
  • txrx0000 7 minutes ago
    Not really. The largest IQ4_XS quant here is still worth it because Bonsai doesn't offer larger quants. They could beat it if they made a quaternary variant though, I don't know why they're stopping at ternary.