---
format: "aidr-story-markdown/v1"
id: "8834e7c0e216deda6ae1bf8abb77ac5e24f92a8fdb4a5eba82c3280b8425d5bd"
canonical_url: "https://aidr.today/8834e7c0?lang=en"
title: "Shapelearn Qwen 3.8 27B (13.1 GB VRAM)"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-18T02:04:19.000Z"
category: "Models"
topics: ["anthropic","claude","multi-agent","open-source"]
source_urls: ["https://byteshape.com/blogs/Qwen3.8-27B/"]
summary: "ByteShape released Shapelearn Qwen 3.8 27B, a model requiring 13.1 GB of VRAM."
---

# Shapelearn Qwen 3\.8 27B \(13\.1 GB VRAM\)

> [Open the canonical story](<https://aidr.today/8834e7c0?lang=en>)

**Published:** 2026-09-18T02:04:19.000Z
**Category:** Models
**Topics:** anthropic, claude, multi\-agent, open\-source

## Summary

ByteShape released Shapelearn Qwen 3\.8 27B, a model requiring 13\.1 GB of VRAM\.

## Sources

- [Story source](<https://byteshape.com/blogs/Qwen3.8-27B/>)

