kerasformers/gemma-3-12b-it

See our collection for all versions of Gemma 3.

Run Gemma 3 with Keras 3: JAX, PyTorch, or TensorFlow

kerasformers/gemma-3-12b-it

Paper: Gemma 3 Technical Report (arXiv:2503.19786) · HF Papers

Gemma 3 is Google's open Gemma family with a multimodal (image + text) decoder with a SigLIP vision encoder: RMSNorm, GeGLU, RoPE with a long-context rope scaling, grouped-query attention, alternating local/global attention, and (4B+) a SigLIP image encoder feeding soft image tokens into the decoder. Base checkpoints are for completion; -it variants are instruction-tuned.

For more details, see Google's original model card.

Pure-Keras 3 conversion of google/gemma-3-12b-it for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an instruction-tuned checkpoint: use the chat template via Gemma3Processor.

Quick start

import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from PIL import Image
from kerasformers.models.gemma3 import Gemma3Generate, Gemma3Processor

model = Gemma3Generate.from_weights("kerasformers/gemma-3-12b-it")
processor = Gemma3Processor.from_weights("kerasformers/gemma-3-12b-it")

inputs = processor(conversation=[
    {"role": "user", "content": [
        {"type": "image", "image": Image.open("cat.jpg")},
        {"type": "text", "text": "Describe this image in one sentence."},
    ]}
])
outputs = model.generate(**inputs, max_new_tokens=64)
print(processor.decode(outputs[0]))

All Gemma 3 variants load the same way with from_weights("kerasformers/<variant>"):

Variant	Hub	Type
gemma-3-270m	kerasformers/gemma-3-270m	text / base
gemma-3-270m-it	kerasformers/gemma-3-270m-it	text / instruct
gemma-3-1b-pt	kerasformers/gemma-3-1b-pt	text / base
gemma-3-1b-it	kerasformers/gemma-3-1b-it	text / instruct
gemma-3-4b-pt	kerasformers/gemma-3-4b-pt	multimodal / base
gemma-3-4b-it	kerasformers/gemma-3-4b-it	multimodal / instruct
gemma-3-12b-pt	kerasformers/gemma-3-12b-pt	multimodal / base
gemma-3-12b-it	kerasformers/gemma-3-12b-it	multimodal / instruct
gemma-3-27b-pt	kerasformers/gemma-3-27b-pt	multimodal / base
gemma-3-27b-it	kerasformers/gemma-3-27b-it	multimodal / instruct

Tips

• Set KERAS_BACKEND before importing Keras / kerasformers.
• Loads in bfloat16 by default (the weights are bf16). Pass load_dtype="float32" for full precision, or quantization="int8" to shrink further.
• gemma-3-1b is text-only — use gemma-3-4b-it or larger for images.
• See Gemma 3 docs and Loading Weights.
• Upstream safetensors still work via the hf: prefix, e.g. Gemma3Generate.from_weights("hf:google/gemma-3-12b-it").

Special Thanks

A huge thank you to the Google Gemma authors for creating and releasing these models.

License: Gemma (gated). Accept the license on the upstream Hub card before downloading.