Downloads · 30 days
126
6% of all-time downloads
Qwen3-Embedding-4B-W4A16_ASYM
dolfsai/Qwen3-Embedding-4B-W4A16_ASYM
Qwen3-Embedding-4B-W4A16_ASYM is a feature extraction model from dolfsai. Use it when you need embeddings to search or compare text. The card lists the license as apache-2.0.
This is a compressed version of Qwen/Qwen3-Embedding-4B using llm-compressor with the following scheme: W4A16ASYM
All-time downloads
2.1K
Public
Parameters
4.5B
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 100%
Parameter types
How the weights are stored.
I323.7B · 82%
Base models
Model card
From the Hugging Face model README
prudant/Qwen3-Embedding-4B-W4A16_ASYM
This is a compressed version of Qwen/Qwen3-Embedding-4B using llm-compressor with the following scheme: W4A16_ASYM
Important: You MUST read the following guide for correct usage of this model here Guide
(Check pooling configuration in VLLM and best pooling mode for this model)
Model Details
- Original Model: Qwen/Qwen3-Embedding-4B
- Quantization Method: AWQ
- Compression Libraries: llm-compressor
- Calibration Dataset: HuggingFaceH4/ultrachat_200k (1024 samples)
- Optimized For: Inference with vLLM
- License: same as original model
- Task
- Feature Extraction
- Type
- qwen3
- License
- apache-2.0
- Languages
- es, en
- Created
- Aug 23, 2025
- Updated
- Aug 23, 2025