Bonsai 27B Runs Qwen 3.6 27B at 10x less memory.

The new Bonsai 27B Model from PrismML is Qwen3.6 27B - a beloved workhorse for many - into something you can run on local computer. 10x less memory and a much more modest file size while still benchmarking 95% of the original FP16 model. Of course, no model is perfect, but if you have been wanting to run Qwen3.6 27B and dont have the computer or headroom - you finally can. The Ternary format is much smarter, but takes a bit more compute. The Binary model is enough to fit into a phone form factor. Imagine 27B, even remotely, in your pocket. That is now a reality. *Links* : Blog: https://prismml.com/news/bonsai-27b Whitepaper: https://github.com/PrismML-Eng/Bonsai... HuggingFace Collection: https://huggingface.co/collections/pr... WebGPU Demo: https://huggingface.co/spaces/webml-c... *As of now you MUST use these forks to run these models* PrismML LLama.cpp repo: https://github.com/PrismML-Eng/llama.cpp MLX Repo: https://github.com/PrismML-Eng/mlx AnythingLLM: https://github.com/Mintplex-Labs/anyt... OpenComputer: https://github.com/Mintplex-Labs/anyt... *Chapters* : 0:00 The promise of Bonsai 27B 0:57 Lets look at the benchmarks and models 2:52 Why would you choose Bonsai 27B? 5:22 How to run it locally... 6:00 Download the right binary 7:27 Download the model from HuggingFace 7:50 (Shortcut) - Use webGPU! 8:17 Picking the right files from HuggingFace 9:00 Start the llama-server and use the UI 10:52 How does it work with simple agent tasks? 12:12 What about using a whole computer and a longer task? 14:53 My thoughts on Bonsai 27B 15:26 Is this the end of the AI bubble?