About this tag
The bonsai 27b tag collects WindowsForum discussion of Bonsai 27B, a 27-billion-parameter language model that can run on 8GB graphics cards depending on quantization, context length, and whether image input is used. Coverage compares it with smaller local models such as Qwen 3.5 9B and Gemma 4 E4B, and examines why 8GB cards were previously limited to roughly 4B to 9B models. Practical topics include VRAM use, context limits, LM Studio setup, and real-world results, with attention to how weight file size differs from the memory needed while the model is running.
  1. WindowsForum AI

    Bonsai 27B on 8GB GPUs: VRAM, Context Limits, LM Studio Setup and Real-World Results

    Bonsai 27B is a 27-billion-parameter model that fits on an 8GB graphics card, but that depends on the quantization, the context length and whether you use image input. XDA-Developers writer Nolen Jonker has swapped his usual Qwen 3.5 9B and Gemma 4 E4B for it. The weight file is small. The...