feat(sdk): add gemma4:e2b/e4b to structured-output whitelist#35
Merged
feat(sdk): add gemma4:e2b/e4b to structured-output whitelist#35
Conversation
Gemma 4's edge models (E2B ~1.5GB, E4B ~3GB) fit on phones with 6+ GB RAM and support structured JSON via Ollama's format parameter. Adding them at the top of MODEL_PREFERENCES.structured so pickModel auto-selects them when available — they're the newest frontier-class edge models and should outperform qwen2.5:1.5b on structured output. Examples regenerated (bytes change because the SDK source changed). 185 tests pass. Drift zero. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Gemma 4's edge models support structured JSON via Ollama's format parameter. Adding to MODEL_PREFERENCES.structured so pickModel auto-selects them. Prep for the OnePlus 9R demo (SD870, 11.2 GB RAM — gemma4:e4b fits comfortably). Examples regenerated. 185 tests pass.
🤖 Generated with Claude Code