# Quantization-aware training
Gemma 3 1b It Qat Bnb 4bit
Gemma 3 is a lightweight open model series launched by Google, built on Gemini technology, supporting multimodal input and text output.
Image-to-Text
Transformers

G
unsloth
23
1
Gemma 3 4b It Qat Unsloth Bnb 4bit
Gemma 3 is a lightweight, cutting-edge open model series launched by Google, built on Gemini model technology, supporting multimodal input and text output.
Image-to-Text
Transformers

G
unsloth
918
1
Gemma 3 27b It Qat
Gemma is a lightweight open model series launched by Google, built on Gemini model technology. Gemma 3 is a multimodal model supporting text and image inputs with text outputs, featuring a 128K large context window and multilingual capabilities.
Image-to-Text
Transformers

G
unsloth
168
2
Gemma 3 12b It Qat Bnb 4bit
Gemma 3 is a lightweight multimodal model launched by Google. It is built on the same technology as Gemini, supports text and image input, and outputs text content. It has a large context window of 128K and supports over 140 languages.
Image-to-Text
Transformers

G
unsloth
2,180
0
Gemma 3 12b It Qat Unsloth Bnb 4bit
Gemma 3 is a lightweight and state-of-the-art open model family launched by Google, built on the same research and technology as the Gemini model. It supports multimodal input and text output.
Image-to-Text
Transformers

G
unsloth
1,422
1
Gemma 3 12b It Qat GGUF
Gemma is a lightweight, advanced open model series from Google, built using the technology behind the Gemini models. Gemma 3 is a multimodal model capable of processing both text and image inputs to generate text outputs.
Text-to-Image
G
unsloth
4,943
5
Gemma 3 12b It Qat
Gemma 3 is a lightweight, state-of-the-art multimodal open-source model launched by Google. It can process text and image inputs and generate text outputs, suitable for various text generation and image understanding tasks.
Image-to-Text
Transformers

G
unsloth
952
2
Amoral Gemma3 4B V2 Qat Q4 0 GGUF
Apache-2.0
A 4B-parameter quantization-aware training model based on Gemma3 architecture, focused on analytical neutral responses and factual integrity in controversial topics
Large Language Model English
A
soob3123
619
4
Amoral Gemma3 12B V2 Qat
Apache-2.0
A quantization-aware trained version based on Gemma-3-12B, focused on generating analytically neutral responses, especially suitable for sensitive and controversial topics.
Large Language Model
Transformers English

A
soob3123
286
10
Google Gemma 3 27b It Qat GGUF
A quantized version based on Google Gemma 3's 27-billion parameter instruction-tuned model, generated using quantization-aware training (QAT) weights, supporting multiple quantization levels to meet different hardware requirements.
Large Language Model
G
bartowski
14.97k
31
Gemma 3 27b It Qat Bf16
Gemma 3 27B IT QAT BF16 is a version of the Gemma series of models released by Google. It has undergone quantization-aware training (QAT) and is converted to the BF16 format, suitable for the MLX framework.
Image-to-Text
Transformers

G
mlx-community
178
2
Gemma 3 12b It Qat Int4 Unquantized
Gemma 3 is a lightweight multimodal open model from Google, supporting text and image inputs with text output, featuring a 128K large context window and multilingual capabilities.
Image-to-Text
Transformers

G
google
1,358
9
Gemma 3 4b It Qat Int4 Unquantized
Gemma 3 is a lightweight multimodal open model launched by Google, supporting text and image input and generating text output. The 4B version has undergone instruction tuning and quantization-aware training, making it suitable for deployment in resource-constrained environments.
Image-to-Text
Transformers

G
google
541
3
Gemma 3 1b It Qat Int4 Unquantized
Gemma is Google's lightweight advanced open model series, built with the same technology as Gemini, supporting multimodal input and text generation.
Large Language Model
Transformers

G
google
507
3
Gemma 3 27b It Qat Compressed Tensors
Gemma 3 is a lightweight and advanced open model series launched by Google, built on the same research and technology as the Gemini model. This version is an instruction-tuned model with 27B parameters, using quantization-aware training (QAT) and compressed tensor technology.
Image-to-Text
G
gaunernst
1,985
6
Gemma 3 12b It Qat Compressed Tensors
Gemma 3 is Google's lightweight cutting-edge open model family, built on the same research and technology used to create Gemini models. This model is multimodal, capable of processing both text and image inputs to generate text outputs.
Text-to-Image
G
gaunernst
867
1
Gemma 3 4b It Qat Compressed Tensors
Gemma 3 4B is a lightweight multimodal model based on Google technology. It supports text and image inputs and generates text outputs, suitable for deployment in resource-constrained environments.
Image-to-Text
Safetensors
G
gaunernst
2,478
1
Gemma 3 12b It Qat Q4 0 GGUF
Gemma is a lightweight, cutting-edge open model series from Google, built on Gemini technology. The 12B version is a multimodal model supporting text and image input, featuring a 128K large context window and support for over 140 languages.
Image-to-Text
G
Mungert
1,008
3
Ibert Roberta Large
I-BERT is a pure integer-quantized version of RoBERTa-large, using INT8 to store parameters and integer operations for inference, achieving up to 4x inference acceleration.
Large Language Model
Transformers

I
kssteven
45
0
Featured Recommended AI Models