Qwen3.8-27B

Alibaba Qwen

Catalogue only Open weights

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

Qwen3.8-27B is a dense vision-language model with a 262,144-token context that the vendor says can be extended to one million tokens. Thinking mode is enabled by default and can be disabled per request, with reasoning depth controlled by a reasoning_effort parameter. It is published under Apache-2.0 and is the smallest model of the Qwen3.8 generation.

Specifications

Provider
Alibaba Qwen (CN)
Context window
262k
Parameters
27.78B
Modalities
text, vision
License
apache-2.0 · licence
Open weights
yes
Release date
05 Aug 2026
Tasks
reasoning, coding, vision, multilingual-support, summarization

Languages

Strong: en, zh

Adequate: de, fr, es, it, pt, ru, ja, ko, ar

Languages

Strong

  • en
  • zh

Adequate

  • de
  • fr
  • es
  • it
  • pt
  • ru
  • ja
  • ko
  • ar

Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

When to use it

Strengths

  • 262k-token context, extensible to 1M per the vendor
  • native image and video understanding
  • switchable thinking mode with adjustable reasoning effort
  • Apache-2.0 licence

Limits

  • benchmark claims on the card are self-reported
  • dense 27B weights need a large-memory accelerator at BF16
  • no evaluation has been run by LLM EU