qwen3-embedding-8b-generic-gpu · azureml v1
# Qwen3 Embedding 8B Webgpu Gpu This is the GPU (WebGPU)-optimized variant of qwen3-embedding-8b, a text embedding model from the Qwen3 family developed by Alibaba Cloud and optimized by Microsoft. #…
azureFoundry/azureml/qwen3-embedding-8b-generic-gpu@1
Qwen3 Embedding 8B Webgpu Gpu
This is the GPU (WebGPU)-optimized variant of qwen3-embedding-8b, a text embedding model from the Qwen3 family developed by Alibaba Cloud and optimized by Microsoft.
Model Details
- Model Type: Text Embedding (ONNX)
- Parameters: 8 billion
- Context Length: 32K tokens
- Embedding Dimension: Up to 4096
- Quantization: KLD Gradient quantization
- Target Device: GPU (WebGPU)
- Execution Provider: WebGPUExecutionProvider
- Supported Languages: 100+
Intended Use
This model is optimized for local execution on devices with GPU (WebGPU) hardware acceleration using Foundry Local.
Capabilities
- Text retrieval and semantic search
- Code retrieval
- Text classification and clustering
- Bitext mining
- Multilingual and cross-lingual retrieval
License
This model is licensed under Apache 2.0. See license details.
Source
Specifications & capabilities
- Input
- text
- Output
- text
- Max output · tokens
- 1
Provider specifications & access
1–1 / 1
- source model id
- azureml/qwen3-embedding-8b-generic-gpu@1
- hosting
- foundry-managed-compute
- license
- apache-2.0
- max output tokens
- 1
Safety assessments
1–1 / 1
26 / 100
- source id
- stanfordFMTI
- canonical model id
- azureFoundry/azureml/qwen3-embedding-8b-generic-gpu@1
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Alibaba
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 26 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–1 / 1
- field
- max_output_tokens
- value
- 1
- normalized value
- 1
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models