{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T18:12:09.555Z","data":{"recordId":"wsa_zyxu572igk7x","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/GrootTeam/Groot-19B-A3B-261023","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-29T00:58:41.173Z","detectedPublishedAt":"2026-10-23T08:47:29.000Z","rights":"original"}],"claims":[{"id":"32f89fb1-5198-413e-b746-f36763e4802c","kind":"capability","statement":"The model has about 19B total parameters and activates about 3B per token.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"Groot-19B-A3B-261023 has 19B total parameters and activates about 3B per token.","rights":"original"}}]},{"id":"bcfa4c6f-7d3e-4cfb-8b11-875f55dff7e7","kind":"capability","statement":"It supports a native context length of 262,144 tokens and natively supports tool calling.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"It has a default context length of **262,144** tokens and natively supports tool calling.","rights":"original"}}]},{"id":"778dbf0f-e2ea-4075-941c-8de276a53edd","kind":"availability","statement":"BF16, FP8, NVFP4, and GGUF (Q4_K_M) weights are released.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"**Where it runs.** We release BF16, **FP8**, **NVFP4** and **GGUF (Q4_K_M)** weights.","rights":"original"}}]},{"id":"1c846d76-1ad2-47e4-ab59-68fdd372fd7d","kind":"deployment","statement":"The BF16 weights fit on a single 48GB or 80GB GPU.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"The BF16 weights (about 39 GB) fit on a single 48GB or 80GB GPU.","rights":"original"}}]},{"id":"21e9a42f-20e8-4384-a82c-51d065dc056f","kind":"capability","statement":"With YaRN scaling, the effective context window can be extended to roughly 1M tokens.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"YaRN is built into both vLLM and SGLang, and a scaling factor of 4.0 grows the usable window to roughly 1M tokens.","rights":"original"}}]},{"id":"21833e66-694a-4c40-a2eb-e1ca9df91dc8","kind":"recommendation-relevant","statement":"The source reports that it beats Qwen3.6-35B-A3B and Gemma-4-26B-A4B on 12 of 16 benchmarks.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"**Accuracy.** Groot-19B-A3B-261023 beats both Qwen3.6-35B-A3B and Gemma-4-26B-A4B on 12 of the 16 benchmarks, for example Terminal Bench 2.1 (52.10 vs 43.82 / 26.52), NL2Repo-Bench (35.65 vs 28.77 / 16.55) and LongBench v2 (62.03 vs 48.12 / 47.99).","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."}}}