Skip to content

feat(gallery): add Qwen3.8 Flash Next - #11763

Open
localai-org-maint-bot wants to merge 1 commit into
masterfrom
cron/model-gallery-20260828
Open

feat(gallery): add Qwen3.8 Flash Next#11763
localai-org-maint-bot wants to merge 1 commit into
masterfrom
cron/model-gallery-20260828

Conversation

@localai-org-maint-bot

Copy link
Copy Markdown
Collaborator

Description

Add Qwen3.8-Flash-Next to the model gallery with Q4 and Q8 llama.cpp variants. Each entry includes every GGUF shard, the shared BF16 vision projector, and SHA256 values verified from Hugging Face x-linked-etag headers.

The default Q4 entry declares the Q8 build as a variant so LocalAI can select the higher-quality quantization when it fits.

Notes for Reviewers

Verification:

  • go run ./.github/ci/modelslist.go ./gallery/index.yaml
  • go test ./core/gallery -ginkgo.focus='gallery/index.yaml variant invariants'
  • git diff --check

The full go test ./core/gallery/... run passed 375 specs and failed three existing network-dependent specs because this environment returns Forbidden for their GitHub/raw test URLs.

Signed commits

  • Yes, I signed my commits.
  • Documentation updated (docs/content/) for user-facing changes, or not applicable

Add the Q4 and Q8 GGUF builds with the shared vision projector.\nThe variant pair lets LocalAI select the build that fits available memory.\n\nAssisted-by: Codex:gpt-5
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