Is it possible to release a version with low bit quantization?

#2
by lan0004 - opened

It works really well with OpenClaw, especially for those who want a local low-bit quantization version.

seconded, I would like a q2_k as that's all i can load

I suggest you try this: https://huggingface.co/ubergarm/Step-3.5-Flash-GGUF

The IQ4_XS quant seems perfect, really well made.

Sign up or log in to comment