Huihui Gemma 4 31B Abliterated v2
Chat with AI using text and images/video
Chat with AI using text and images/video
Rewrite AI drafts to read like a person; facts kept. 12B
Choice, scale, yes/no and ranking in one encoder pass
Convert JSON input into formatted text output
Chat with an AI using text, images, audio, or video
Run GGUF directly on your browser!
Generate adult novel text from a prompt
Generate custom worlds using CPU-powered web service
Generate research hypotheses and gaps from your question
Play the task agent against a simulated terminal
A small decision model decides when Gemma 4 is needed
A 20K storyteller in your browser. WebGPU + WebAssembly.
Access a free OpenAI‑compatible Qwen 3.8‑27B chat endpoint
Transcribe audio files into text
Chat with Qwen3.8 Flash Next using this hosted demo.
Benchmark base LMs (10M–1B) on CPU — speed and quality
Fill Mask
Multimodal decision making and retrieval with one encoder
Explore Arabic model responses side‑by‑side
Ground desktop UI elements from a screenshot and task.
Get a checklist for your farm question
Transcribe audio or YouTube video into text
Generate answers to your questions
Run a 1-bit 27B LLM locally in your browser on WebGPU