Q8_0 GGUF?
#1
by
MrParivir
- opened
As per title, I don't suppose it would be possible to get a Q8_0 GGUF for this model? I know the performance gain is likely low but it's non-zero and I run all local models under 70B at Q8_0 for fair comparison.
No worries if not but I figured it couldn't hurt to ask.
EDIT: mradermacher has now got the full quant and i-quant set for this model so this isn't required anymore.
Entropicengine
changed discussion status to
closed