Skip to content

Add Qwen models resource card#286

Open
qualiaMachine wants to merge 2 commits intomainfrom
claude/add-qwen-resource-card-1zu40
Open

Add Qwen models resource card#286
qualiaMachine wants to merge 2 commits intomainfrom
claude/add-qwen-resource-card-1zu40

Conversation

@qualiaMachine
Copy link
Copy Markdown
Contributor

Summary

  • Adds a new resource card for the Qwen family of open-weight large language and multimodal models by Alibaba Cloud
  • Covers key features (dense/MoE architectures, multimodal capabilities, long-context support, multilingual proficiency, permissive licensing)
  • Documents model variants: Qwen2.5 (dense), Qwen2.5-Coder, Qwen2.5-Math, Qwen2.5-VL, Qwen2.5-Omni, and QwQ-32B
  • Includes timeline context, usage tips, related benchmarks, and links to related Nexus resources

Test plan

  • Verify the .qmd file renders correctly with Quarto
  • Confirm the resource card appears in the Toolbox/Models listing
  • Check that all external links are valid
  • Review category tags for consistency with existing cards

https://claude.ai/code/session_016JvaKWyhwUEUzSezwXpDVb

claude added 2 commits March 25, 2026 16:32
Add a new resource card for the Qwen family of open-weight large language
and multimodal models by Alibaba Cloud. Covers key features, model variants
(dense, MoE, code, math, vision-language, omni), timeline context, usage
tips, and related resources.

https://claude.ai/code/session_016JvaKWyhwUEUzSezwXpDVb
- Replace variant bullet list with a detailed comparison table showing
  each model family, modality, sizes, and concrete use cases
- Add size selection guidance (0.5B–3B, 7B–14B, 32B–72B)
- Add GPU memory estimation table across FP16, INT8, and 4-bit quantization
- Add hands-on Python snippets to profile VRAM usage and compare sizes,
  precisions, and quantization methods

https://claude.ai/code/session_016JvaKWyhwUEUzSezwXpDVb
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants