GLM-4.6V-exl3 / README.md
turboderp's picture
Update README.md
e06c0fd verified
metadata
license: mit
base_model: zai-org/GLM-4.6V
base_model_relation: quantized
quantized_by: turboderp
tags:
  - exl3

EXL3 quants of GLM-4.6V

⚠️ Requires ExLlamaV3 v0.0.18 (or v0.0.17 dev branch)

Base bitrates:

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

Optimized:

2.13 bits per weight
2.32 bits per weight
2.55 bits per weight
2.80 bits per weight
3.13 bits per weight
3.55 bits per weight
4.07 bits per weight