Skip to content

feat(core): add image+video support for Qwen3.6-35B-A3B quant variants #4106

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tanzhenxin merged 2 commits into from
May 15, 2026
Merged

feat(core): add image+video support for Qwen3.6-35B-A3B quant variants #4106

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c6981ad
feat(core): add image+video support for Qwen3.6-35B-A3B quant variants
Dinsmoor May 13, 2026
3d87a43
Merge branch 'QwenLM:main' into fix-qwen3.6-image-support
Dinsmoor May 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions packages/core/src/core/modalityDefaults.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,14 @@ describe('defaultModalities', () => {
expect(m.audio).toBeUndefined();
});

it('returns image + video for qwen3.6-35b variants', () => {

@wenshao wenshao May 14, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[Suggestion] Test name says "variants" (plural) but only tests a single variant qwen3.6-35b-a3b-nvfp4. The regex /^qwen3\.6-35b/ is broad (matches all qwen3.6-35b-* models), so testing only one variant leaves a gap where future regex narrowing could silently regress other variants.

Consider either:

  • Renaming to 'returns image + video for qwen3.6-35b-a3b-nvfp4' to accurately reflect scope, or
  • Adding additional test cases for bare qwen3.6-35b and a quant-stripped variant like qwen3.6-35b-fp16

Nice to have: Add a normalization test with provider prefix (e.g., dashscope/qwen3.6-35b-a3b-nvfp4) in the normalization describe block.

— DeepSeek/deepseek-v4-pro via Qwen Code /review

const m = defaultModalities('qwen3.6-35b-a3b-nvfp4');
expect(m.image).toBe(true);
expect(m.video).toBe(true);
expect(m.pdf).toBeUndefined();
expect(m.audio).toBeUndefined();
});

it('returns text-only for qwen-turbo', () => {
expect(defaultModalities('qwen-turbo')).toEqual({});
});
Expand Down
2 changes: 2 additions & 0 deletions packages/core/src/core/modalityDefaults.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,8 @@ const MODALITY_PATTERNS: Array<[RegExp, InputModalities]> = [

// Qwen coder / text models: text-only
[/^qwen3-coder-/, {}],
// Qwen3.6-35B-A3B (local quant variants) — image + video
[/^qwen3\.6-35b/, { image: true, video: true }],
[/^qwen/, {}],

// -------------------
Expand Down