Skip to content
Model library

Qwen

Qwen3.8 27B

Qwen3.8 27B on one dedicated NVIDIA A100 SXM4 80 GB in US-MD-1, United States. $1,899/month per endpoint, subject to current qualified capacity.

Language models
Parameters
27B
Input / output
Text, images, PDFs / text
Context / output
Up to 32K context tokens · up to 4K output tokens per request
Request capacity
Each endpoint serves up to 8 requests at once; additional requests wait briefly in a bounded queue
Hardware
1× NVIDIA A100 SXM4, 80 GB
Location
US-MD-1, United States

Build with it

  • Draft emails and documents
  • Research and brainstorm
  • Summarize long documents
  • Ask questions over images and PDFs
  • Extract structured JSON, including invoice fields
Original model card & license