Feature Extraction
Transformers
Safetensors
qwen3
fp8
compressed-tensors
llm-compressor
vllm
embedding
text-embeddings-inference
Instructions to use DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic") model = AutoModel.from_pretrained("DCC-BS/Qwen3-Embedding-4B-FP8-Dynamic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "task": "WikipediaRetrievalMultilingual", | |
| "metric": "ndcg_at_10", | |
| "languages": [ | |
| "de", | |
| "en", | |
| "it" | |
| ], | |
| "tolerance": 0.01, | |
| "baseline": { | |
| "model": "Qwen/Qwen3-Embedding-4B", | |
| "task": "WikipediaRetrievalMultilingual", | |
| "metric": "ndcg_at_10", | |
| "scores": { | |
| "de": 0.90665, | |
| "en": 0.93437, | |
| "it": 0.89927 | |
| } | |
| }, | |
| "candidate": { | |
| "model": "models/Qwen3-Embedding-4B-FP8-Dynamic", | |
| "task": "WikipediaRetrievalMultilingual", | |
| "metric": "ndcg_at_10", | |
| "scores": { | |
| "de": 0.90653, | |
| "en": 0.93531, | |
| "it": 0.89944 | |
| } | |
| }, | |
| "created_at": "2026-08-05T14:38:16+00:00" | |
| } | |