Shapelearn Qwen 3.8 27B (13.1 GB VRAM)

44 points by syntaxing 5 hours ago

From my own test. It's not faster than the unsloth model.

Disclarer: I'm unsing Vulkan on an AMD GC.

Aged like milk

Mashimo - an hour ago

In the comments it reads like bonsei falls apart on longer running tasks.
txrx0000 - an hour 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.