This is just my IQ4_XS quant of https://huggingface.co/failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5

Also included is my generated imatrix data file, generated on 200 x 2048 tokens of Wiki.Train.Raw against Q8_0 (i dont have enough RAM + VRAM to do the full fp16).

Downloads last month
8
GGUF
Model size
70.6B params
Architecture
llama

4-bit

Inference API
Unable to determine this model's library. Check the docs .