mistralai/Voxtral-Mini-4B-Realtime-2602 Automatic Speech Recognition β’ 4B β’ Updated Mar 11 β’ 1.23M β’ 861
Running on Zero Agents Featured 1.94k Qwen3-TTS Demo π 1.94k Generate custom speech from text, voice descriptions, or samples
Running Featured 131 Ministral WebGPU β‘ 131 Frontier multimodal AI, running entirely in your browser.
Running on CPU Upgrade Agents 1.02k Open VLM Leaderboard π 1.02k VLMEvalKit Evaluation Results Collection
Running on Zero MCP 408 Multimodal OCR π 408 Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
docling-project/SmolDocling-256M-preview Image-Text-to-Text β’ 0.3B β’ Updated Sep 17, 2025 β’ 30.6k β’ 1.61k
Running on Zero Agents Featured 1.78k Dia 1.6B π― 1.78k Generate realistic dialogue from a script, using Dia!