turboderp's picture
Update README.md
8a783a5 verified
|
raw
history blame
648 Bytes
---
license: apache-2.0
---
EXL2 quants of [granite-3.1-8b-instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct)
[4.00 bits per weight](https://huggingface.co/turboderp/granite-3.1-8b-instruct-exl2/tree/4.0bpw)
[5.00 bits per weight](https://huggingface.co/turboderp/granite-3.1-8b-instruct-exl2/tree/5.0bpw)
[6.00 bits per weight](https://huggingface.co/turboderp/granite-3.1-8b-instruct-exl2/tree/6.0bpw)
[8.00 bits per weight](https://huggingface.co/turboderp/granite-3.1-8b-instruct-exl2/tree/8.0bpw)
[measurement.json](https://huggingface.co/turboderp/granite-3.1-8b-instruct-exl2/blob/main/measurement.json)