Search FoxAI
AI Models 85011
- StreamRender-H3↗
Efficient-Large-Model
StreamRender-H3 splits an interactive world into a **Code Game Engine** and a **Streaming Diffusion Render**. The engine keeps the world state in code (maps, physics, rules) and streams a semantic map for every frame. A two-step streaming video model built on MiniMax-H3 Ref2VA renders those maps into photorealistic video as the player drives, with the look set by a reference image and a prompt. - Two denoising steps per chunk in the distilled student. - Diffusion render of 217.96 ms per streaming step on 8 GB200 GPUs, a 3.67× speedup over the PyTorch baseline. - Fast Causal H3 VAE decodes 2 latent frames at 720p in 24 ms on one GB200, built by a self-improving agent loop. There are five distinct model components. Qwen's two storage formats are the same model. The causal decoder is constructed directly from its architecture configuration and student checkpoint; no native H3 video VAE checkpoint is needed. Streaming reference encoding uses TAE, and video decoding uses the trained causal decoder.
- polyglot-ko-12.8b↗
EleutherAI
- Qwen3.8-27B-W3Rot-INT3-Paiton-RDNA4↗
EliovpAI
- EuroLLM-9B-MeditronFO↗
EPFLiGHT
- GLM-OCR-ita-mlx-8bit↗
fabriziosalmi
- mms-tts-jac↗
facebook
- mms-tts-poh-dialect_western↗
facebook
- paraformer-zh↗
funasr
- gajosep↗
gajosep
- gemini-4-argon-thinking-low↗
Google
The special offer group model is implemented by partially eligible accounts, using specific parameter requests to invoke Gemini 3.8 Flash. It has been confirmed that upstream traffic is indeed routed to Gemini 4. These are different checkpoints within Gemini 4; reportedly, b performs slightly better than a, but b currently has a lower level of reasoning. The exact IQ should be assessed through actual customer testing.
