Tag
A new ternary quantized version of Qwen3.6 27B, called Bonsai 27B, allows running the model on 12GB GPUs with 10x less memory and 95% of original performance, making it accessible for local deployment.
Discussion on the feasibility of 1-bit models like Bonsai 8b and 27b, which achieve small file sizes while remaining functional, questioning their primary use cases and future.
Prism-ML published benchmarks for their Bonsai-27B model.
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.
PrismML announces Bonsai 27B, a 1-bit and ternary quantized version of Qwen3.6 27B that runs on phones and laptops, retaining 90-95% of baseline performance with a 3.9GB footprint, enabling agentic and multimodal on-device AI.
Prism ML released Ternary-Bonsai-27B, a ternary-quantized version of Qwen3.6-27B that retains 95% of FP16 intelligence at a ~7.2 GB footprint, enabling full 27B-class reasoning on laptops and single GPUs with speeds up to 26 tok/s on Apple M5 Pro.
Jane Street engineers introduce strace-ui, an interactive terminal UI for strace that simplifies syscall debugging with filtering, PID tracking, and man page integration, and highlight the TUI renaissance enabled by their Bonsai framework.