fp8 quantization for gemma3-12b-it model
#2
by
ShaoServient
- opened
Hi,
Could you quantize the 12b model to fp8, or could you share here how did you do that.
I tried a couple of ways but none work.
Thank you
Hi,
The fp8 quantized version of gemma-3-12b-it is available, requested to please checkout.
Best Regards,
Thank You
MISHANM
changed discussion status to
closed