4 bits quantized GGUF weight of phi-3-mini-4k-instruct. Mlx compatible.
Official model: https://huggingface.co./microsoft/Phi-3-mini-4k-instruct-gguf (not supported by mlx)
Please note that the official phi-3-mini-4k-instruct.gguf model is of llama-2 architecture as stated in the paper (https://huggingface.co./papers/2404.14219)
- Downloads last month
- 193
Inference API (serverless) is not available, repository is disabled.