Add Qwen3-1.7B iOS and macOS export support - #196
Open
stikves wants to merge 2 commits into
Open
Conversation
Register Qwen3-1.7B in the model registry for both macOS (4-bit) and iOS (mixed 4-bit/8-bit palettized) platforms. Add the mixed quantization config yaml and HuggingFace metadata entry. Perplexity: 20.96 (float16) → 21.19 (mixed 4/8-bit, 5.43 BPW).
stikves
requested review from
alejandro-isaza,
carinapeng,
kevchengcodes,
pkmandke and
tjia1818
August 26, 2026 00:42
tjia1818
reviewed
Aug 26, 2026
| | Model | Parameters | macOS | iOS | | ||
| | ---------- | ---------- | ----- | --- | | ||
| | Qwen3 0.6B | 0.6B | Yes | Yes | | ||
| | Qwen3 1.7B | 1.7B | Yes | Yes | |
Contributor
There was a problem hiding this comment.
let's make sure we tested AOT compilation + on-device specialization for this iOS variant.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Register Qwen3-1.7B in the model registry for both macOS (4-bit) and iOS (mixed 4-bit/8-bit palettized) platforms. Add the mixed quantization config yaml and HuggingFace metadata entry.
Perplexity: 20.96 (float16) → 21.19 (mixed 4/8-bit, 5.43 BPW).
Closes #116