Category

Bonsai Demo

Runs the Bonsai family of quantized LLMs locally (including vision-capable 27B): provides scripts and demo UIs to run 1-bit and ternary Bonsai models on macOS (Metal), Linux/Windows (CUDA/Vulkan/ROCm), or CPU, with long context, tool-calling and an optional Open WebUI agent demo.

OmniVoice

Converts text to natural-sounding speech across 600+ languages in a zero-shot way, with short-reference voice cloning and fine-grained voice-design controls; uses a diffusion language-model-style architecture to balance quality and very low inference latency.

Mistral Medium 3.5 128B

A dense 128B multimodal model with a 256k context window, configurable reasoning effort, and native function-calling for agentic workflows. Supports text+image input, multilingual output, and is released on Hugging Face under a Modified MIT license with revenue-based exceptions.

VoxCPM2

Generates 48kHz multilingual speech from text using a tokenizer-free diffusion-autoregressive TTS architecture, supporting natural-language voice design, controllable cloning, and low-latency streaming. Notable for a 2B-parameter backbone and built-in AudioVAE super-resolution (16k→48k).

GLM-5.1

Generates and iterates on long‑horizon agentic plans and code — designed to stay productive across many rounds of tool calls and experiments. Emphasizes iterative reasoning, stronger repo/terminal automation and code generation than GLM‑5, and can be served locally for research and autonomous-agent workloads.

Gemma 4 31B JANG_4M CRACK (v2) — dealignai

Multimodal image-text-to-text fork of Gemma 4 (31B) using a 'CRACK v2' abliteration — tuned for conversational vision inputs and thinking-mode support in JANG v2 safetensors format. Recommended to run in vMLX; published by dealignai.

Lyra 2.0: Explorable Generative 3D Worlds

Generates persistent, explorable 3D worlds from a single image by synthesizing long-range, geometry-consistent video and reconstructing it into an explicit 3D Gaussian scene. Intended for internal research use under NVIDIA's research license.

Granite-4.1-8B

An 8B-parameter, instruction-tuned long-context LLM optimized for instruction following, tool-calling, and multilingual dialogue — supports 131072-token context and common NLP tasks such as summarization, QA, code, and RAG.

Granite-4.1-30B

A 30B-parameter, instruction-tuned language model built for long-context text generation, conversational agents, and tool-calling. It combines supervised fine-tuning and RL alignment, supports 131,072-token context, and is optimized for tasks like summarization, code, and RAG.

ERNIE-Image

An open text-to-image generation model built on an 8B Diffusion Transformer that focuses on layout-sensitive, text-heavy, and instruction-following image synthesis. Notable for accurate text rendering, structured/compositional generation (posters, comics), and ability to run on consumer 24GB GPUs when paired with prompt enhancement.

MiniMax-M2.7

Text-generation LLM designed for agentic workflows: supports multi-agent 'Agent Teams', skill stacks and model self-evolution. Ships on Hugging Face with deployment guides (vLLM, Transformers, SGLang) and is positioned for engineering, tool-calling and productivity use cases.

HY-World 2.0

Generates and reconstructs navigable, editable 3D worlds from text, single images, multi-view photos, or video; outputs meshes and Gaussian Splatting assets and includes WorldMirror 2.0 for fast multi-view reconstruction. Suited for research and production pipelines that import assets into engines; requires substantial GPU resources.