ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-04-16 07:26:56 +00:00
Code Issues Actions 18 Packages Projects Releases Wiki Activity

chore(model gallery): add gemma-3-4b-it-qat (#5118)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-04 10:23:56 +02:00 committed by GitHub
parent 128612a6fc
commit 31a7084c75
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
gallery/index.yaml
View File

@ -96,6 +96,24 @@
- filename: gemma-3-12b-it-q4_0.gguf
sha256: 6f1bb5f455414f7b46482bda51cbfdbf19786e21a5498c4403fdfc03d09b045c
uri: huggingface://vinimuchulski/gemma-3-12b-it-qat-q4_0-gguf/gemma-3-12b-it-q4_0.gguf
- !!merge <<: *gemma3
name: "gemma-3-4b-it-qat"
urls:
- https://huggingface.co/google/gemma-3-4b-it
- https://huggingface.co/vinimuchulski/gemma-3-4b-it-qat-q4_0-gguf
description: |
This model corresponds to the 4B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.
Thanks to QAT, the model is able to preserve similar quality as bfloat16 while significantly reducing the memory requirements to load the model.
You can find the half-precision version here.
overrides:
parameters:
model: gemma-3-4b-it-q4_0.gguf
files:
- filename: gemma-3-4b-it-q4_0.gguf
sha256: 2ca493d426ffcb43db27132f183a0230eda4a3621e58b328d55b665f1937a317
uri: huggingface://vinimuchulski/gemma-3-4b-it-qat-q4_0-gguf/gemma-3-4b-it-q4_0.gguf
- !!merge <<: *gemma3
name: "qgallouedec_gemma-3-27b-it-codeforces-sft"
urls: