Downloads · 30 days
55
0% of all-time downloads
Qwen3-Reranker-8B-W4A16-G128
boboliu/Qwen3-Reranker-8B-W4A16-G128
Qwen3-Reranker-8B-W4A16-G128 is a text classification model from boboliu. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
GPTQ Quantized Qwen/Qwen3-Reranker-8B with Ultrachat, THUIR/T2Ranking and m-a-p/COIG-CQIA for calibration set.
All-time downloads
43.5K
Public
Parameters
8.2B
6.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.1 GB · 100%
Parameter types
How the weights are stored.
I326.9B · 84%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-Reranker-8B-W4A16-G128
GPTQ Quantized Qwen/Qwen3-Reranker-8B with Ultrachat, THUIR/T2Ranking and m-a-p/COIG-CQIA for calibration set.
What's the benefit?
VRAM Usage: more than 24G -> 19624M, make it available on 3090/4090. (w/o FA2, according to Embedding model's result).
What's the cost?
I think <5% accuracy, further evaluation on the way...
The Embedding one shows ~0.7%.
How to use it?
pip install compressed-tensors optimum and auto-gptq / gptqmodel, then goto the official usage guide.
- Task
- Text Classification
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Jun 7, 2025
- Updated
- Jun 7, 2025