DQN-Labs/dqnGPT-gemma3-adapter
TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kPublished:Feb 21, 2026License:gemmaArchitecture:Transformer Warm

The DQN-Labs/dqnGPT-gemma3-adapter is a 1 billion parameter language model, converted to MLX format from Google's Gemma-3-1b-it. This model is designed for efficient deployment and inference within the MLX ecosystem, leveraging its 32768 token context length. Its primary utility lies in providing a compact yet capable model for MLX-based applications, suitable for general-purpose conversational AI and text generation tasks.

Loading preview...