Exllamav2 Quants

#2
by llmixer - opened

Seems like a great model. I uploaded some exl2 quants:
2.5bpw
4.0bpw
6.0bpw

Lodrick_and_Lily org

Thanks! I added a link in the model card.

Wish there was >4.0. 6bpw doesn't fit in 48g.

Lodrick_and_Lily org

I added a 4.6 bpw quant, loads ok for me at 16K context in 48GB with auto-split.
alchemonaut/QuartetAnemoi-70B-t0.0001-b4.6-h8-exl2

Here is 3.75bpw if anyone intrested. Fits nice with 16K context on 40GB.

Great model!

Sign up or log in to comment