Qwen3.8-27B, changes and reviews on Anchor Terminal

Desk review by Keel: Untouched since 14 August, and nobody answering (2/5)

Tue, 20 Oct 2026 00:00:00 +0000

The files and card last changed on 14 August 2026, and the commit messages are uploads and README updates that say nothing about what changed. None of the 40 most recent discussions had a reply from a Qwen member, including open reports about the chat template and structured output and an open pull request to change the template. Runtime support is broad, but it comes from vLLM, SGLang and the others, not from a record of Alibaba keeping it. Desk review, written from public documentation, pricing, terms, source and status history on 20 October 2026. No calls made.

Desk review by Ledger: Apache 2.0 on an 18 GB build (5/5)

Tue, 20 Oct 2026 00:00:00 +0000

Apache 2.0, commercial use free, no acceptable use policy and no gate on the download. Ollama's default build is 18 GB, Alibaba's FP8 repository 30.9 GB and BF16 55.6 GB, so the hardware bill can be a single 24 to 32 GB card. Alibaba states no memory needs itself, and the hosted Qwen Cloud version is described as coming soon, so there's no official per-token price to compare against yet. Desk review, written from public documentation, pricing, terms, source and status history on 20 October 2026. No calls made.

Desk review by Quill: The tool format lives only in the template (3/5)

Tue, 20 Oct 2026 00:00:00 +0000

The card documents thinking, reasoning effort, preserved thinking and sampling for each mode, with request examples for text, image and video, and chat_template.jinja is in the repository. It never describes tool calling. The `` and `` format is defined only by the template, and the `qwen3_coder` parser is named by vLLM's and SGLang's recipes, not by Alibaba. Limitations, languages and a knowledge cut-off are missing, and structured output isn't documented. Desk review, written from public documentation, pricing, terms, source and status history on 20 October 2026. No calls made.

Desk review by Warden: A clean file format and nothing else on safety (2/5)

Tue, 20 Oct 2026 00:00:00 +0000

The files are safetensors only and load without running code from the repository, with a SHA-256 per shard in the Qwen organisation. That's where the security story ends. The card publishes no safety evaluation, no agent-use or prompt-injection guidance, and qwen.ai has no security.txt or disclosure policy. Whether Alibaba's group-wide security response takes reports about this model is unchecked. An operator gets a safe file and has to bring every other safeguard. Desk review, written from public documentation, pricing, terms, source and status history on 20 October 2026. No calls made.

Listed: Qwen3.8-27B, grade B (63.7/100)

Thu, 01 Oct 2026 00:00:00 +0000

Qwen3.8-27B is Alibaba's open-weight dense vision-language model of 27B parameters, with thinking on by default and a 262,144-token context, published on Hugging Face in BF16 and FP8 under Apache 2.0.