Skip to content

feat(gallery): add LFM2.5 VL 3B variants - #11494

Open
localai-org-maint-bot wants to merge 1 commit into
masterfrom
cron/model-gallery-20260813-run4
Open

feat(gallery): add LFM2.5 VL 3B variants#11494
localai-org-maint-bot wants to merge 1 commit into
masterfrom
cron/model-gallery-20260813-run4

Conversation

@localai-org-maint-bot

Copy link
Copy Markdown
Collaborator

Description

Add Liquid AI's newly released LFM2.5-VL-3B model to the gallery with its official Q4_K_M and Q8_0 GGUF builds. Both variants use the official F16 vision projector and reference SHA256 values verified against Hugging Face LFS metadata and repeated x-linked-etag responses.

The default Q4_K_M entry links the Q8_0 build through the gallery variant mechanism.

Notes for Reviewers

Validation performed:

  • Parsed all 1,658 gallery entries with gopkg.in/yaml.v3.
  • Checked unique entry names and the new variant reference invariants.
  • Confirmed each model page and artifact URL returns HTTP 200.
  • Matched all three committed SHA256 values against Hugging Face immediately before push.
  • Ran git diff --check.

go test ./core/gallery could not run in the fresh worktree because generated gRPC code was absent. make prepare-test then failed while downloading protoc because the environment proxy returned HTTP 403.

Signed commits

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

The gallery entry is the user-facing model metadata; no separate documentation page is required.

Add the official Q4_K_M and Q8_0 GGUF builds with the F16 vision projector.

Assisted-by: Codex:gpt-5.6-sol
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