Skip to content

Staff picks: add Qwen3.8 27B at the top - #11

Open
danyurkin wants to merge 1 commit into
AtomicBot-ai:mainfrom
danyurkin:staff-picks-qwen3.8-27b
Open

Staff picks: add Qwen3.8 27B at the top#11
danyurkin wants to merge 1 commit into
AtomicBot-ai:mainfrom
danyurkin:staff-picks-qwen3.8-27b

Conversation

@danyurkin

@danyurkin danyurkin commented Aug 14, 2026

Copy link
Copy Markdown

Adds AtomicChat/Qwen3.8-27B-GGUF as the first entry in models/staff-picks.json, and refreshes updated_at.

order: 0 puts it above Muse Glimmer (order: 1) and stays inside the promoted head, which the client defines as everything below FAMILY_SEQUENCE_START = 10. The sort path uses pick.order ?? Number.POSITIVE_INFINITY and the coercion uses Number.isFinite(r.order), so a 0 is preserved rather than treated as absent.

categories omits vision deliberately. The base model Qwen/Qwen3.8-27B is multimodal, but this quant repo ships no mmproj-*.gguf projector and the GGUF architecture is the text-only qwen35, 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

@danyurkin danyurkin changed the title Staff picks: добавить Qwen3.8 27B в самый верх Staff picks: add Qwen3.8 27B at the top Aug 14, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant