Shapelearn Qwen 3.8 27B (13.1 GB VRAM) 5 hours ago (byteshape.com) 4 comments syntaxing Reply Add to library _ache_ 2 hours ago From my own test. It's not faster than the unsloth model.Disclarer: I'm unsing Vulkan on an AMD GC. sheo 2 hours ago Aged like milkhttps://news.ycombinator.com/item?id=49746618 Mashimo 1 hour ago In the comments it reads like bonsei falls apart on longer running tasks. txrx0000 1 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.
_ache_ 2 hours ago From my own test. It's not faster than the unsloth model.Disclarer: I'm unsing Vulkan on an AMD GC.
sheo 2 hours ago Aged like milkhttps://news.ycombinator.com/item?id=49746618 Mashimo 1 hour ago In the comments it reads like bonsei falls apart on longer running tasks. txrx0000 1 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.
txrx0000 1 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.
From my own test. It's not faster than the unsloth model.
Disclarer: I'm unsing Vulkan on an AMD GC.
Aged like milk
https://news.ycombinator.com/item?id=49746618
In the comments it reads like bonsei falls apart on longer running tasks.
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.