Llama-3-70B-exl2 / README.md
turboderp's picture
Update README.md
e915155 verified
EXL2 quants of [Llama-3 70B](https://huggingface.co/NousResearch/Meta-Llama-3-70B)
[2.40 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/2.4bpw)
[2.80 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/2.8bpw)
[3.00 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/3.0bpw)
[3.50 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/3.5bpw)
[4.00 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/4.0bpw)
[4.50 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/4.5bpw)
[5.00 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/5.0bpw)
[6.00 bits per weight](https://huggingface.co/turboderp/Llama-3-70B-exl2/tree/6.0bpw)
[measurement.json](https://huggingface.co/turboderp/Llama-3-70B-exl2/blob/main/measurement.json)