{"slug": "ternary-bonsai-2-27b", "title": "Ternary Bonsai 2 27B", "summary": "Ternary Bonsai 2 27B, a ternary-weight multimodal model built on a Qwen3.8 27B base, ships at roughly 6GB with weights restricted to {-1, 0, +1} at 1.76 bits per weight with FP16 group scales, according to the model's provider. The 27.4B-parameter model offers hybrid attention, a 262k context window, and vision input, and retains 98.2 percent of the FP16 baseline on a 20-benchmark thinking suite while running on llama.cpp and MLX. The provider reports the model adds no embedded watermarks or provenance metadata to generated output, and no per-token API provider pricing is tracked for it yet.", "body_md": "# Ternary Bonsai 2 27B\n\nconsumer\nTernary-weight multimodal model on a Qwen3.8 27B base: weights are values in {-1, 0, +1} at 1.76 bits per weight with FP16 group scales, so the full 27B model ships at roughly 6GB. Hybrid attention, 262k context, vision input. Keeps 98.2 percent of the FP16 baseline on a 20-benchmark thinking suite. Runs on llama.cpp and MLX.\n\nAI-generated content marks\n\nThe provider reports that this model does not add embedded watermarks or provenance metadata to generated output.\n\n- 27.4B\n- 262k\n- apache 2.0\n- Undisclosed\n- Sep 2026\n\nSave your hardware and every model page answers the real question: will it run on *your* machine, and how fast?\n\n[Join free - save your rig →](https://tokenstead.ai/login?return_to=%2Fonboarding)\n\n## Or run it in the cloud\n\n        No per-token API provider pricing tracked for Ternary Bonsai 2 27B yet.\n        For flagship list prices, see the\n        [calculator](https://tokenstead.ai/calculator).\n      \n\n## Inference cost over time\n\nData accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.", "url": "https://wpnews.pro/news/ternary-bonsai-2-27b", "canonical_source": "https://tokenstead.ai/models/ternary-bonsai-2-27b", "published_at": "2026-09-20 14:00:53+00:00", "updated_at": "2026-09-20 14:25:30.199775+00:00", "lang": "en", "topics": ["large-language-models", "ai-products", "ai-tools", "computer-vision", "ai-infrastructure"], "entities": ["Ternary Bonsai 2 27B", "Qwen3.8 27B", "llama.cpp", "MLX", "OpenRouter"], "alternates": {"html": "https://wpnews.pro/news/ternary-bonsai-2-27b", "markdown": "https://wpnews.pro/news/ternary-bonsai-2-27b.md", "text": "https://wpnews.pro/news/ternary-bonsai-2-27b.txt", "jsonld": "https://wpnews.pro/news/ternary-bonsai-2-27b.jsonld"}}