{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-30T03:36:10.644Z","data":{"recordId":"wsa_4h4d9vqxqz5g","score":0.975,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/Qwen/Qwen3.8-27B","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:27:38.878Z","detectedPublishedAt":"2026-08-05T08:22:59.000Z","rights":"original"}],"claims":[{"id":"c98b2314-8903-4513-9ffa-29c64165b6d5","kind":"availability","statement":"The repository contains model weights and configuration files in Hugging Face Transformers format.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"> This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.","rights":"original"}}]},{"id":"6fa18454-6b85-4b99-a97e-c884b206d05a","kind":"capability","statement":"Qwen3.8-27B is a native vision-language model that understands images and videos.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.","rights":"original"}}]},{"id":"37338be3-410f-4261-b0d3-c2385c749783","kind":"capability","statement":"Thinking mode is on by default and can be disabled per request.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"- **Flexible Thinking Control**: Thinking mode is on by default and can be disabled per request; reasoning depth can be tuned with `reasoning_effort`, and reasoning context from historical messages is retained via `preserve_thinking`.","rights":"original"}}]},{"id":"8e329afc-2311-4be3-83f4-3be224e81ba7","kind":"capability","statement":"Reasoning depth can be tuned with the reasoning_effort setting.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- **Flexible Thinking Control**: Thinking mode is on by default and can be disabled per request; reasoning depth can be tuned with `reasoning_effort`, and reasoning context from historical messages is retained via `preserve_thinking`.","rights":"original"}}]},{"id":"ba381500-dfc8-47bb-a3cc-522034d2a52a","kind":"capability","statement":"The model has a native context length of 262,144 tokens and is extensible to 1,000,000 tokens.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- Context Length: 262,144 natively and extensible up to 1,000,000 tokens.","rights":"original"}}]},{"id":"7e562988-37b8-4373-a0fe-5818036820c7","kind":"capability","statement":"The model artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, and TokenSpeed.","citations":[{"source":1,"supportProbability":0.94,"supports":true,"quote":{"text":"> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.","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."}}}