Llama-3_1-Nemotron-Ultra-253B-v1-Q3_K_M imatrix iQ3 Abliterated or Uncensored
#870
by
wa999
- opened
Llama-3_1-Nemotron-Ultra-253B-v1-Q3_K_M imatrix iQ3 Abliterated or Uncensored
wa999
changed discussion title from
Llama-3_1-Nemotron-Ultra-253B-v1-Q3_K_M imatrix iQ3
to Llama-3_1-Nemotron-Ultra-253B-v1-Q3_K_M imatrix iQ3 Abliterated or Uncensored
This comment has been hidden (marked as Off-Topic)
mradermacher
changed discussion status to
closed
Oops, sorry for the previous confusing comment, wrong issue - the model is not yet supported by llama.cpp, but it is sitting in the queue. Once support arrives we will quant it.
Not sure why you said this is not supported by llama.cpp?
Nicoboss did this one already:
https://huggingface.co/nicoboss/Llama-3_1-Nemotron-Ultra-253B-v1-GGUF/tree/main
Requesting imatrix iQ3 Abliterated or Uncensored
https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
