Skip to content

Add support for GLM-OCR model #1143

Open

Description

@msluszniak

Problem description

HF repository: https://huggingface.co/zai-org/GLM-OCR

Proposed solution

Classic support of a model via RNE.

Alternative solutions

Not applicable.

Benefits to React Native ExecuTorch

Great addition to RNE ecosystem. Provide much better results than currently available OCR.

Additional context

No response

Activity

  1. added
    modelIssues related to exporting, improving, fixing ML models
    on May 12, 2026
  2. added this to the v0.10.0 milestone on Aug 11, 2026
  3. removed this from the v0.10.0 milestone on Aug 17, 2026
  4. msluszniak commented on Aug 17, 2026

    @msluszniak
    MemberAuthor

    This model turns out to be way too slow aka 5-10s per image. For now, we don't progress with it until something will change this performance.

  5. added
    blockedIssue blocked by some problems (but not other issue, use relationship -> blocker instead)
    on Aug 17, 2026
  6. msluszniak commented on Oct 22, 2026

    @msluszniak
    MemberAuthor

    Smaller alternatives if GLM-OCR stays too slow: PaddleOCR-VL-1.5 (0.9B, Apache 2.0), SmolDocling-256M.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    blockedIssue blocked by some problems (but not other issue, use relationship -> blocker instead)modelIssues related to exporting, improving, fixing ML models

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions