GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
chibifire
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
chibifire
Model Tree
google/gemma-4-12B-it
Input Modalities
Output Modalities
Supported Functionality
This repo is a mirror of Google DeepMind's Gemma 4 12B instruction-tuned QAT Q4_0 checkpoint. QAT trains the model to keep its quality when its weights are stored at Q4_0 precision. It holds the half-precision weights from the QAT pipeline in safetensors form, with the tokenizer, chat template, processor config and generation config. Use it as a pinned copy of the upstream weights for local inference and for further conversion.
Load it with Transformers.
python
from transformers import AutoProcessor, AutoModelForMultimodalLM MODEL_ID = "chibifire/gemma-4-12B-it-qat-q4_0-unquantized"processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForMultimodalLM.from_pretrained(MODEL_ID, dtype="auto", device_map="auto")For prompts, chat template, thinking modes and multimodal input, read the upstream model card and the Gemma documentation.
Apache 2.0, under the Gemma 4 licence terms at https://ai.google.dev/gemma/docs/gemma_4_license. These terms travel with the weights. Keep this link when you copy or redistribute them.
from transformers import AutoProcessor, AutoModelForMultimodalLM MODEL_ID = "chibifire/gemma-4-12B-it-qat-q4_0-unquantized"processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForMultimodalLM.from_pretrained(MODEL_ID, dtype="auto", device_map="auto")