Quantization
This model is quantized from Phi-3-mini-4k-instruct using channel-wise symmetric int4 quantization optimized for NPU inference with the OpenVINO Toolkit.
Limitations
Check the original model card for limitations.
Legal information
The original model is distributed under MIT license. More details can be found in the original model card.
- Downloads last month
- 117
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for tngtech/Phi-3-mini-4k-instruct-sym-int4-channelwise-ov
Base model
microsoft/Phi-3-mini-4k-instruct