NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
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.

sheo 2 hours ago [-]
Mashimo 2 hours ago [-]
In the comments it reads like bonsei falls apart on longer running tasks.
txrx0000 2 hours 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.
rguiscard 30 minutes ago [-]
I wonder the same thing for Bonsai 2. ByteShape offers 5 models from IQ2_XXS-2.56bpw (8.8GB), IQ3_XXS-2.88bpw (9.9GB), IQ3_XS-3.01bpw (10.4GB), IQ3_S-3.23bpw (11.0GB) to IQ4_XS-3.84bpw (13.1GB). Their benchmarks show gradual improvement with size and users can pick one to fit theirs need. Bonsai-2-27B now is about 8.6GB. It might be good to have a quaternary version around 10-11GB to fit a computer with 16-24GB RAM.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 07:51:06 GMT+0000 (Coordinated Universal Time) with Vercel.