qwen3.5:0.8b

Upstream reference: Qwen3.5-0.8B

Publisher: Qwen Team, Alibaba Cloud

The publisher describes this post-trained vision-language checkpoint as a small model intended for prototyping, research and task-specific fine-tuning.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Language-model parameters

0.8 billion Source

Native context

262,144 tokens Source

Default generation mode

Non-thinking; thinking mode available Source

Upstream license label

Apache-2.0 Source

Publisher-described uses

• Prototyping, task-specific adaptation and research using text and visual inputs. Source

Reference limitations

• Serving implementations can disable vision or lower the configured context; published architecture does not establish enabled runtime behavior. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Qwen3.5-0.8B official documentation — Qwen Team, Alibaba Cloud. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Alibaba Cloud Qwen — official site
• Ollama
• Hugging Face

Where qwen3.5:0.8b comes from

Named in 4 observation pages

• 14B-32B local models — all 47 · V1
• Models as data workers · V1
• The capability ladder — execution-verified · V1
• The minimum viable model probe · V1