unsloth/gemma-4-E4B-it-qat-GGUF
Added Gemma official chat template update
Rename MTP GGUFs
Add MTP -hf usage under the model image
Add smart Q4_0 drafter into MTP/ and list it
Use smart Q4_0 as root MTP drafter (near-lossless, ~half size)
Add Jun 9 update: MTP support with link to MTP guide
Add MTP README for QAT drafter (-hf auto-discovery + explicit usage)
Remove old-named MTP drafters (superseded by renamed copies)
Add root-level mtp- drafter for -hf auto-discovery; rename MTP/ drafters to -MTP suffix
Add Gemma 4 E4B QAT MTP drafter under MTP/
Updated mmproj for QAT
Updated mmproj for QAT
Updated mmproj for QAT
Update README.md
Fix base_model name: add -qat-
Prepend Unsloth banner + tags
Update base_model to q4_0-unquantized QAT master
Add files using upload-large-folder tool
Add gemma-4-E4B-it-qat-UD-Q2_K_XL.gguf (mobile wNa8o8 faithful: TQ2_0/Q4_0/Q8_0)
gemma-4-E4B-it-qat-Q4_0.gguf
Add model card from official Gemma 4 QAT unquantized release
Add files using upload-large-folder tool
Add files using upload-large-folder tool
initial commit