@OpenBMB: Thanks to @_akhaliq for contributing MiniCPM-V 4.6 Hugging Face demo, which allowed us to test the gradio.Server featur…
Summary
OpenBMB thanks @_akhaliq for contributing a Hugging Face demo for MiniCPM-V 4.6, using Gradio server for flexible frontend customization.
View Cached Full Text
Cached at: 05/24/26, 08:18 AM
Thanks to @_akhaliq for contributing MiniCPM-V 4.6 Hugging Face demo, which allowed us to test the gradio.Server feature. The flexible frontend customization provides an excellent experience for both developers and users! https://huggingface.co/spaces/openbmb/MiniCPM-V-4.6-Demo/discussions/1… https://huggingface.co/collections/openbmb/minicpm-v-46…
openbmb/MiniCPM-V-4.6-Demo · use gradio server
Source: https://huggingface.co/spaces/openbmb/MiniCPM-V-4.6-Demo/discussions/1 Upload images, audio, and videos by dragging in the text input, pasting, orclicking here.
Tap or paste here to upload images
Similar Articles
@_akhaliq: MiniMax-Music3 gradio workflow is out https://huggingface.co/spaces/akhaliq/MiniMax-Music3-workflow…
MiniMax-Music3 gradio workflow is now available as a Hugging Face Space, enabling easy use of the music generation model.
Any Custom Frontend with Gradio's Backend
Hugging Face introduces `gradio.Server`, a new tool that allows developers to use Gradio's backend infrastructure (queuing, hosting) with custom frontends built using React, Svelte, or plain HTML/CSS/JS.
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
MiniCPM-o 4.5 is a 9B parameter multimodal model featuring Omni-Flow, a framework enabling real-time full-duplex interaction where the model can simultaneously perceive and respond proactively. It achieves state-of-the-art open-source performance comparable to Gemini 2.5 Flash and runs on edge devices with less than 12GB RAM.
Kijai/MiniMax-H3_comfy
A Hugging Face repository hosting MiniMax-H3 models converted for ComfyUI usage, along with a Lightx2v distill LoRA for faster inference.
@DJLougen: This is a huge commitment, thank you as always to @huggingface and co for their commitment to local opportunities
GLM-5.2 is now free to use with Hugging Face Inference Providers for the next 6 hours, supporting open-source AI.