mistralai/Voxtral-Mini-4B-Realtime-2602 Automatic Speech Recognition β’ 4B β’ Updated 9 days ago β’ 760k β’ 719
Running on Zero Featured 1.72k Qwen3-TTS Demo π 1.72k Generate speech audio via voice design, cloning, or preset speakers
Running Featured 130 Ministral WebGPU β‘ 130 Frontier multimodal AI, running entirely in your browser.
Running on Zero MCP 404 Multimodal OCR π 404 demo of a collection of impressive ocr vl models on hf
docling-project/SmolDocling-256M-preview Image-Text-to-Text β’ Updated Sep 17, 2025 β’ 77.2k β’ 1.61k
Running on Zero Featured 1.76k Dia 1.6B π― 1.76k Generate realistic dialogue from a script, using Dia!