Tag
Ternary Bonsai 27B, a large language model, is demonstrated running locally on an NVIDIA RTX 5090 GPU, requiring under 6GB of memory and enabling end-to-end agentic workflows on consumer hardware.
PrismML announces Bonsai 27B, a multimodal model based on Qwen3.6 27B that can run on a phone, enabling local multi-step reasoning, tool use, and long-context workflows.
The author built an autonomous development pipeline and benchmarked it by running the same project using a local 27B model on a modified RTX 4090 versus cheap cloud LLM APIs.
Introduces a new 27B post-trained model that distills positives from Fable and Kimi 2.7 Coder, with links to download.