Repository navigation
catalog: the gemma-4-26B-A4B-it rows carry Google's MTP head - #88
Merged
Merged
Conversation
The four catalog files of basecompute/gemma-4-26B-A4B-it are replaced on the Hub by the same bundles with google/gemma-4-26B-A4B-it-assistant embedded in their speculator section (basert add-speculator, BaseRT 0.4.4, f16 head, head_version 1): new sizes and sha256, speculator gemma4-mtp, speculator_version 1, as the E2B and E4B rows carry theirs.
IsuraManchanayake
marked this pull request as ready for review
November 5, 2026 13:14
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The four
basecompute/gemma-4-26B-A4B-itrows get the embedded-head files' sizes and sha256,speculator: gemma4-mtpandspeculator_version: 1, as the E2B and E4B rows do (#84). The files are the catalog bundles withgoogle/gemma-4-26B-A4B-it-assistantembedded bybasert add-speculator(BaseRT 0.4.4, f16 head, head version 1); every model tensor keeps its bytes. Draft until the Hub PR (basecompute/gemma-4-26B-A4B-it, discussions/1) is merged.