This is an MLX-format conversion of Google's Gemma 3 27B instruction-tuned model, quantized to 8-bit precision for efficient inference on Apple Silicon devices. The model is a multimodal language model capable of understanding both images and text, allowing it to process visual content and generate text responses based on combined image and text inputs. It's optimized for running on MLX, Apple's machine learning framework, making it suitable for on-device inference with reduced memory requirements compared to the full-precision version.
available local models on Mirai:
available local models on Mirai:
Name
Quantisation
Size
gemma-3-1b-it
uint8
1B
Quant.
uint8
Size
1B
gemma-3-27b-it
uint8
27B
Quant.
uint8
Size
27B
gemma-3-4b-it
uint8
4B
Quant.
uint8
Size
4B
gemma-3-1b-it-4bit
uint8
1B
Quant.
uint8
Size
1B
gemma-3-1b-it-8bit
uint8
1B
Quant.
uint8
Size
1B
gemma-3-27b-it-4bit
uint8
27B
Quant.
uint8
Size
27B
gemma-3-27b-it-8bit
uint8
27B
Quant.
uint8
Size
27B
gemma-3-4b-it-4bit
uint8
4B
Quant.
uint8
Size
4B
gemma-3-4b-it-8bit
uint8
4B
Quant.
uint8
Size
4B
This is an MLX-format conversion of Google's Gemma 3 27B instruction-tuned model, quantized to 8-bit precision for efficient inference on Apple Silicon devices. The model is a multimodal language model capable of understanding both images and text, allowing it to process visual content and generate text responses based on combined image and text inputs. It's optimized for running on MLX, Apple's machine learning framework, making it suitable for on-device inference with reduced memory requirements compared to the full-precision version.
available local models on Mirai:
Name
Quantisation
Size
gemma-3-1b-it
uint8
1B
Quant.
uint8
Size
1B
gemma-3-27b-it
uint8
27B
Quant.
uint8
Size
27B
gemma-3-4b-it
uint8
4B
Quant.
uint8
Size
4B
gemma-3-1b-it-4bit
uint8
1B
Quant.
uint8
Size
1B
gemma-3-1b-it-8bit
uint8
1B
Quant.
uint8
Size
1B
gemma-3-27b-it-4bit
uint8
27B
Quant.
uint8
Size
27B
gemma-3-27b-it-8bit
uint8
27B
Quant.
uint8
Size
27B
gemma-3-4b-it-4bit
uint8
4B
Quant.
uint8
Size
4B
gemma-3-4b-it-8bit
uint8
4B
Quant.
uint8
Size
4B