Skip to content

chore(core-ai): host starter model bundles #238

Open

Description

@grabbou

The Core AI starter models table (website/src/docs/core-ai/models.md) links community-exported bundles for some models and marks the rest as "Planned Callstack-hosted bundle":

  • qwen2.5-1.5b-instruct (language)
  • sana-sprint-0.6b (image generation)
  • efficient-sam-vitt (image segmentation)
  • yolos-tiny, yolos-base (object detection)

Export these with the apple/coreai-models 1.0 recipes (iOS presets) and host them, e.g. under a Callstack Hugging Face org, then update the table with direct links. Hosting our own copies also removes the dependency on third-party uploads for the models that are linked today.


Follow-up from #219.

🤖 Generated with Claude Code

Activity

  1. grabbou commented on Oct 26, 2026

    @grabbou
    ContributorAuthor

    Status after the #237 work:

    Hosted (exported with the coreai-models 1.0 recipes, tested on an iPhone 17 Pro), and listed on the models page:

    • Language: grabbou/qwen3-0.6b-CoreAI (replaces the third-party link)
    • Image generation: grabbou/FLUX.2-klein-4B-CoreAI
    • Video generation: grabbou/Wan2.1-T2V-1.3B-CoreAI (macOS; iPhone tracked in fix(core-ai): fit video generation in iphone memory #306)
    • Transcription: grabbou/parakeet-tdt-0.6b-v3-CoreAI
    • Embeddings: grabbou/clip-vit-base-patch32-CoreAI
    • Object detection: grabbou/yolos-tiny-CoreAI
    • Segmentation: grabbou/EfficientSAM-Ti-CoreAI, video: grabbou/sam3-video-CoreAI
    • Super-resolution, classification, depth: grabbou/edsr-x2-CoreAI, grabbou/pvt-v2-b0-CoreAI, grabbou/depth-anything-3-small-CoreAI

    Still open from this issue:

    • qwen2.5-1.5b-instruct
    • yolos-base
    • sana-sprint-0.6b: its Gemma-2-2B text encoder is 4.9 GB, which does not fit an iPhone app, so it stays macOS-only

    Moving the hosted exports to a Callstack organization is tracked in #308.

    🤖 Generated with Claude Code

  2. changed the title [-]Core AI: host starter model bundles[/-] [+]chore(core-ai): host starter model bundles[/+] on Nov 1, 2026
  3. apex-sentinel-staging commented on Nov 1, 2026

    @apex-sentinel-staging

    Apex Sentinel · Issue review

    Suggested label: feature

    The issue requests a new enhancement: exporting and hosting specific Core AI starter model bundles under a Callstack-controlled source and updating the documentation links. It identifies concrete models and deliverables, making it actionable.

  4. grabbou commented on Nov 1, 2026

    @grabbou
    ContributorAuthor

    Still open: qwen2.5-1.5b-instruct and yolos-base. Both can be exported with the coreai-models 1.0.0 recipes (coreai.llm.export Qwen/Qwen2.5-1.5B-Instruct --platform iOS and models/yolo/export.py --model hustvl/yolos-base), then hosted next to the others.

    The hosted FLUX.2 export also needs its image-to-image parts (vae_encoder_half, transformer_512_img2img_half) for #343 (#372). The current coreai-models README says --platform iOS includes them, but the hosted export doesn't have them, so the parts may need --components at 1.0.0.

    🤖 Generated with Claude Code

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

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions