Staff picks: add Qwen3.8 27B at the top - #11
Open
danyurkin wants to merge 1 commit into
Open
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds AtomicChat/Qwen3.8-27B-GGUF as the first entry in
models/staff-picks.json, and refreshesupdated_at.order: 0puts it above Muse Glimmer (order: 1) and stays inside the promoted head, which the client defines as everything belowFAMILY_SEQUENCE_START = 10. The sort path usespick.order ?? Number.POSITIVE_INFINITYand the coercion usesNumber.isFinite(r.order), so a0is preserved rather than treated as absent.categoriesomitsvisiondeliberately. The base modelQwen/Qwen3.8-27Bis multimodal, but this quant repo ships nommproj-*.ggufprojector and the GGUF architecture is the text-onlyqwen35, so image input is not possible from these files. Per the schema, categories describe this exact repo rather than the family.Summary claims check out against the model card and the parsed GGUF metadata: hybrid attention with a gate and a state path,
context_length: 262144.No paired MLX entry: the promoted head is GGUF-only by current practice — all four existing head picks are GGUF-only even where an MLX build exists.
🤖 Generated with Claude Code