nanochat-d34-exl3 / README.md
turboderp's picture
Create README.md
c2ec1cb verified
metadata
license: mit
base_model: karpathy/nanochat-d34
base_model_relation: quantized
quantized_by: turboderp
tags:
  - exl3

EXL3 quants of nanochat-d34

⚠️ Requires ExLlamaV3 v0.0.19 (or v0.0.18 dev branch)

Base bitrates:

2.00 bits per weight
3.00 bits per weight
4.00 bits per weight
5.00 bits per weight
6.00 bits per weight