microsoft

/

Phi-4-multimodal-instruct

like 1.16k

Follow

Microsoft 10.3k

Someone has to convert this to GGUF, it shouldn't take long.

After having a gguf version will it be able to do audio tasks, like ASR, speaker diarization, speech synthesis, as well?

Someone has to convert this to GGUF, it shouldn't take long.

I guess GGUF not supported, otherwise we should see it by now.

Perhaps we can count on the ONNX version for CPU only environment for now.
Not sure LM Studio support it though.
https://huggingface.co/microsoft/Phi-4-multimodal-instruct-onnx

@limcheekin You may find this discussion helpful
https://huggingface.co/microsoft/Phi-4-multimodal-instruct/discussions/7#67c4d764491ec4e926ed9d84

Is speaker diarization possible?

@Bash82 the Phi-4-multimodal does not support speaker diarization.