| ▲ | Shapelearn Qwen 3.8 27B (13.1 GB VRAM)(byteshape.com) |
| 42 points by syntaxing 5 hours ago | 4 comments |
| |
|
| ▲ | _ache_ 2 hours ago | parent | next [-] |
| 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 | parent | prev [-] |
| Aged like milk https://news.ycombinator.com/item?id=49746618 |
| |
| ▲ | Mashimo an hour ago | parent | next [-] | | In the comments it reads like bonsei falls apart on longer running tasks. | |
| ▲ | txrx0000 an hour ago | parent | prev [-] | | 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. |
|
