turboderp's picture
Update README.md
4568210 verified
metadata
license: apache-2.0
base_model: Qwen/Qwen3-VL-32B-Instruct
base_model_relation: quantized
quantized_by: turboderp
tags:
  - exl3

EXL3 quants of Qwen3-VL-32B-Instruct

⚠️ Requires ExLlamaV3 v0.0.13 (or v0.0.12 dev branch)

2.00 bits per weight
2.25 bits per weight
2.50 bits per weight
3.00 bits per weight
3.50 bits per weight
4.00 bits per weight
5.00 bits per weight
6.00 bits per weight

SVG Catbench

2.00 bpw
2.00 bpw
2.25 bpw
2.25 bpw
2.5 bpw
2.5 bpw
3.00 bpw
3.00 bpw
3.50 bpw
3.50 bpw
4.00 bpw
4.00 bpw
5.00 bpw
5.00 bpw
6.00 bpw
6.00 bpw
API
API