Hacker News

syntaxing
Shapelearn Qwen 3.8 27B (13.1 GB VRAM) byteshape.com

_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.

sheo2 hours ago

Mashimoan hour ago

In the comments it reads like bonsei falls apart on longer running tasks.

txrx0000an 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.

hn-front (c) 2024 voximity
source