This is the CPU-optimized variant of qwen3-embedding-8b, a text embedding model from the Qwen3 family developed by Alibaba Cloud and optimized by Microsoft.

• Model Type: Text Embedding (ONNX)
• Parameters: 8 billion
• Context Length: 32K tokens
• Embedding Dimension: Up to 4096
• Quantization: KLD Gradient quantization
• Target Device: CPU
• Execution Provider: CPUExecutionProvider
• Supported Languages: 100+

This model is optimized for local execution on devices with CPU hardware acceleration using Foundry Local.

• Text retrieval and semantic search
• Code retrieval
• Text classification and clustering
• Bitext mining
• Multilingual and cross-lingual retrieval

This model is licensed under Apache 2.0. See license details.

• HuggingFace: Qwen3-Embedding-8B

Version: 1

foundryLocal : test license : apache-2.0 licenseDescription : This model is provided under the License Terms available at https://huggingface.co/Qwen/Qwen3-Embedding-8B/blob/main/LICENSE author : Microsoft inputModalities : text outputModalities : text task : embeddings maxOutputTokens : 1 alias : qwen3-embedding-8b directoryPath : v1 promptTemplate supportsToolCalling : false capabilities : embedding supportsReasoning : false reasoningStart reasoningEnd contextLength : 32768 minFLVersion : 0.0.0 disable-maap : true

View in Studio: https://ml.azure.com/registries/azureml/models/qwen3-embedding-8b-generic-cpu/version/1

License: apache-2.0