{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T13:28:24.507Z","data":{"recordId":"wsa_ejvujmg3aard","score":0.839,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/prism-ml/Ternary-Bonsai-2-9B-gguf","publisher":"PrismML","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:02:38.647Z","detectedPublishedAt":"2026-09-23T06:12:31.000Z","rights":"original"},{"n":2,"url":"https://huggingface.co/prism-ml/Ternary-Bonsai-2-9B-mlx-2bit","publisher":"PrismML","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:02:38.647Z","detectedPublishedAt":"2026-10-01T17:06:13.000Z","rights":"original"}],"claims":[{"id":"b63af9ee-68f8-4603-b5e4-0ae8403bc23d","kind":"capability","statement":"The model accepts vision input through a separate mmproj pack.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- **Vision input** through a separate mmproj pack (Q8_0, or BF16 for reference precision), loaded only when an image arrives.","rights":"original"}}]},{"id":"01fc5f39-053e-4185-94fe-4eb44d086e11","kind":"availability","statement":"Three GGUF language-model packings are provided: PTQ1_0, PQ2_0, and Q2_0.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- **Three GGUF packings** of the same weights, consumed directly by custom kernels and never expanded back to FP16: **PTQ1_0** (dense trits, 2.00 GB), **PQ2_0** (2-bit slots, 2.42 GB) and **Q2_0** (2.56 GB).","rights":"original"}}]},{"id":"ba1cae33-6eaa-4ae5-ab74-05020e91b9df","kind":"deployment","statement":"The PrismML llama.cpp fork runs all listed files on CUDA, Metal, and CPU.","citations":[{"source":1,"supportProbability":0.56,"supports":false,"quote":{"text":"| Backends | llama.cpp (CUDA, Metal, CPU) via the PrismML fork |","rights":"original"}}]},{"id":"5bf9bba5-b54d-4ffe-8231-6f212ccb5d9c","kind":"capability","statement":"The model supports vision input through its official vision tower.","citations":[{"source":2,"supportProbability":0.96,"supports":true,"quote":{"text":"- **Vision input** through the official vision tower, carried unrotated in FP16.","rights":"original"}}]},{"id":"8c629a70-799f-417f-a0e5-342aba3c4813","kind":"capability","statement":"The model has a 262K-token context.","citations":[{"source":2,"supportProbability":0.98,"supports":true,"quote":{"text":"- **262K-token context**, inherited from the Qwen3.5-9B hybrid-attention backbone (24 linear-attention and 8 full-attention layers).","rights":"original"}}]},{"id":"5b46416c-75d6-4f7a-b050-5904613652e4","kind":"availability","statement":"The model is available as a downloadable MLX pack on Hugging Face.","citations":[{"source":2,"supportProbability":0.48,"supports":false,"quote":null}]},{"id":"bb7a94cb-3ec6-4609-9edd-f351d3cc3e5d","kind":"deployment","statement":"The pack runs with MLX on Apple Silicon.","citations":[{"source":2,"supportProbability":0.9,"supports":true,"quote":{"text":"A 9B-class vision-language model with ternary transformer weights, packed for MLX on Apple Silicon.","rights":"original"}}]},{"id":"2e668458-89c4-4087-a667-e6285e2cf141","kind":"recommendation-relevant","statement":"The model pack is 3.46 GB on disk.","citations":[{"source":2,"supportProbability":0.99,"supports":true,"quote":{"text":"> **3.46 GB** on disk, language model + vision tower (FP16 language model: ~17.9 GB)","rights":"original"}}]},{"id":"e8eb2c23-7c33-43e0-8032-c5a45751643c","kind":"capability","statement":"The optional trained multi-token-prediction head is intended to help most on copy-heavy work such as code edits and rewrites.","citations":[{"source":2,"supportProbability":0.97,"supports":true,"quote":{"text":"It helps most on copy-heavy work such as code edits and rewrites; on general chat it is about as fast as plain decoding or slightly slower, so plain decoding stays the default.","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}