{"slug": "testing-prismml-bonsai-2", "title": "Testing PrismML Bonsai 2", "summary": "PrismML released Bonsai 2 27B, a ternary-weight compression of Qwen3.8 27B that cuts model size from about 56 GB to 5.9 GB while retaining roughly 98% of the original model's benchmark score. In a hands-on test on an M4 Mac with 24 GB of RAM, the model ran a code review through a Pi coding agent in 30 minutes at about 40 tokens per second, following the tester's codereview.md rules. Bonsai 2 runs on Mac via Metal, on Linux and Windows via CUDA, Vulkan, and ROCm, or on CPU alone.", "body_md": "# Testing PrismML Bonsai 2\n\nPrismML released Bonsai 2 27B this week. It is built on Qwen3.8 27B, but compressed to ternary weights: each weight is +1, 0, or -1 instead of 16 bits. That drops the size from about 56 GB to 5.9 GB. On PrismML’s benchmark suite, it keeps about 98% of the original model’s score. It runs on a Mac (Metal), on Linux or Windows (CUDA, Vulkan, ROCm), or on CPU alone.\n\nI tested it on my M4 Mac with 24 GB of RAM. I wired it to my Pi coding agent and gave it a code review task. It is pretty cool.\n\nBonsai 2 followed my `codereview.md` rules. It checked the change against the other files in the repo, the way I asked it to.\n\nThe full task took 30 minutes. Token speed was about 40 tokens per second, not slow at all.\n\nA 27B model that fits in 6 GB and still runs a real code review on a laptop is a good sign for local coding agents.", "url": "https://wpnews.pro/news/testing-prismml-bonsai-2", "canonical_source": "https://julin.ai/2026/09/19/prismml-bonsai-2/", "published_at": "2026-09-18 12:00:00+00:00", "updated_at": "2026-09-19 11:54:19.379862+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-agents", "ai-research"], "entities": ["PrismML", "Bonsai 2 27B", "Qwen3.8 27B", "Pi", "Mac", "Metal", "CUDA", "Vulkan"], "alternates": {"html": "https://wpnews.pro/news/testing-prismml-bonsai-2", "markdown": "https://wpnews.pro/news/testing-prismml-bonsai-2.md", "text": "https://wpnews.pro/news/testing-prismml-bonsai-2.txt", "jsonld": "https://wpnews.pro/news/testing-prismml-bonsai-2.jsonld"}}