MobileCLIP2-S2 INT8 (ORT + Core ML image)
Locally quantized pack for BonFrame / DeerClip desktop first-run sideload
(视觉模型).
- ORT text (+ visual for Windows/Linux):
text.onnx,text.onnx.data,visual.onnx,visual.onnx.data, tokenizer / config - macOS hybrid image tower:
coreml/MobileCLIP2-S2-Image.mlmodelc+coreml/metadata.json
Upstream: RuteNL/MobileCLIP2-S2-OpenCLIP-ONNX.
Quantized with the in-repo visual-clip:quantize-m2s2 path.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for kingfang008/mobileclip2-s2-int8
Base model
RuteNL/MobileCLIP2-S2-OpenCLIP-ONNX