Practical AI Guides & a Free Claude Code Course

I downloaded it and the file is 5.9 GB, while the same 27B model at full precision takes 54 GB. I ran it through llama.cpp and the reasoning, coding, and tool calling all worked as the benchmarks showed. A team called prism-ml developed a method of storing weights using fewer bits than standard approaches, while keeping 98.2% of the full model accuracy. This means the model answers correctly nearly as often as the 54 GB version, on hardware that does not require anything special.

I tested it through the DeepSeek API and it processed both a long document and an image in the same request. The context window is one million tokens, which is roughly the length of a full novel or a large codebase. During generation the model activates only about 16 billion of its parameters, which is why responses arrive quickly despite the overall scale. It does not run locally and is available through the DeepSeek API or HuggingChat.

I installed the quantized version through Ollama and it fits on a Mac with 32 GB of RAM. Qwen3.8-27B is a model from Alibaba that understands images and videos alongside text, so I tested it on a document with charts and it described the contents correctly. The reasoning depth is adjustable, meaning the model thinks longer on complex questions and skips the reasoning step on simple ones. On a computer-use benchmark called OSWorld, it scores 84.3, which is the level where the model can navigate an interface and take actions on screen without a human.

I gave it a style description and song lyrics and it returned a finished track with vocals. YuE2 is an open music generation model from a research group called m-a-p, and the authors compare the quality to Suno v5 and v6. From my testing, that comparison appears accurate. There is also a cover generation mode where you provide an existing melody and a new style and receive a version in a different genre.

I downloaded the weights and ran it locally. LTX-2.5 is a video generation model from Lightricks that produces video and audio together from a text description or an image. When I generated a multi-scene clip, the character remained consistent across scenes, which was a problem in earlier LTX-Video versions. There is no billing per generation once the model is installed, and it runs through ComfyUI or the command line.

zai-org/ZCode

ZCode is a coding agent from Zhipu AI, the Chinese laboratory that made the GLM models, CogVideoX, and CogView. It is distributed as open source under the Apache 2.0 license. Pre-built packages are available for macOS (Apple Silicon and Intel), Windows (64-bit and ARM64), and Linux, along with a browser interface and a command-line agent. The tool includes a goal format: you describe the final result, and the agent breaks the task into steps and completes them without stopping. It supports screenshots and multimodal queries. You can control the agent through Telegram, Feishu, or WeChat bots. The codebase supports multiple LLM providers through a configuration file.