Repository navigation
chore(gallery): add GLM Flash Maya variants - #12666
Open
localai-org-maint-bot wants to merge 1 commit into
Open
localai-org-maint-bot wants to merge 1 commit into
localai-org-maint-bot wants to merge 1 commit into
Conversation
mudler
force-pushed
the
gallery/20261013-second-pass
branch
from
October 14, 2026 21:33
02069c0 to
9add6df
Compare
Offer Maya S, S24, M, and L builds through the existing GLM group. Pin all weight shards and the vision projector to an HF revision. Document the standard llama.cpp configuration and its limits. Assisted-by: Codex:gpt-6 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
localai-org-maint-bot
force-pushed
the
gallery/20261013-second-pass
branch
from
October 23, 2026 08:09
9add6df to
c83963e
Compare
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Add four GLM-5.3-Flash GGUF builds from peasantsmith/GLM-5.3-Flash-Maya-GGUF: Maya-S v2, S24, M, and L. Link them as variants of
glm-5.3-flash-q4and include every weight shard plus the vision projector.All downloads are pinned to HF revision
f16ee4ba50d8fd2bb726ea1862ca6ca14ba188da. These entries use the existing llama-cpp backend and tokenizer template. They do not enable MTP or Project Maya's SSD expert offloading. Documentation includes an explicit variant installation example and these limits.Notes for Reviewers
x-linked-etagfor all 14 unique artifacts (13 weight shards and the shared projector).general.architecture=glm5-next, present in LocalAI's pinned llama.cpp revisionf2cc7282ce0042641df55e0e563b75e824e2b647.!!mergetags. Checked 2,176 unique names, all variant targets, no nested variants, model/projector file mappings, and pinned hashes. Compared parsed entries with master: exactly four additions and the intended parent variant list change.git diff --checkpassed.go test ./core/gallery -run Test -count=1could not start: proxy.golang.org returnedForbiddenforgithub.com/lufia/plan9stats. No inference smoke test or full model download was performed.c44c32f15. No old models removed.Signed commits
Assisted-by.