Downloads · 30 days
8
11% of all-time downloads
qwen3-embedding-0.6b-awq-int3
phunghuy159/qwen3-embedding-0.6b-awq-int3
qwen3-embedding-0.6b-awq-int3 is a text generation model from phunghuy159. Use it when you need the model to write or continue text. It is set up for transformers.
This repo contains AWQ post-training quantization artifacts for Qwen/Qwen3-Embedding-0.6B.
All-time downloads
70
Public
Repo size
519 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt508 MB · 98%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3
- Access
- Public
- Created
- May 16, 2026
- Updated
- May 16, 2026
- SHA
- d31e019b
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3 Embedding 0.6B AWQ INT3
This repo contains AWQ post-training quantization artifacts for Qwen/Qwen3-Embedding-0.6B.
Files
qwen3-embedding-0.6b-w3-g128-dummy.pt: AWQ search results with scales/clips.qwen3-embedding-0.6b-w3-g128-awq-v2.pt: packed INT3 AWQ state dict.quant_config.json: quantization metadata.- tokenizer/config files copied from the base model.
Quantization
- Method: AWQ PTQ
- Weight bits: INT3
- Group size: 128
- Zero point: true
- Calibration data: dummy local text
- Calibration samples: 16
- Calibration sequence length: 128
Loading note
The packed INT3 checkpoint requires AWQ CUDA kernels/custom AWQ loading code for direct inference. It is not a vanilla AutoModel.from_pretrained model folder.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- Created
- May 16, 2026
- Updated
- May 16, 2026