Isn't that related to architecture? The most recent GPUs and tensor procs have native support for 4-bit(partially) and 8-bit int whereas older GPUs take noticeable performance hits for 8-bit vs fp16/32.
Straight int8 quantization generally does not work for post training quantization of transformers. The distribution of weights includes a significant amount of outlier values that seem to be important to model performance. Apparently quantization aware training can improve things significantly but I haven't seen any developments for llama yet.
Interestingly on the 4 bit front, NVIDIA has chosen to remove int4 support from the next gen Hopper series. I'm not sure folks realize the industry has already moved on. FP8 feels like a bit of a hack, but I like it!