Model Overview

This model, reedmayhew/gemini-3.1-pro-distill-reasoning-12B-QKVO-HF, is a 12 billion parameter language model developed by reedmayhew. It is finetuned from reedmayhew/gemini-3.1-pro-distill-reasoning-12B-QVO-HF and utilizes the gemma3 architecture.

Key Characteristics

• Parameter Count: 12 billion parameters.
• Context Length: Supports a context window of 32768 tokens.
• Training Efficiency: The model was trained significantly faster (2x) by leveraging Unsloth and Huggingface's TRL library.
• License: Distributed under the Apache-2.0 license.

Potential Use Cases

This model is suitable for a variety of general language processing tasks, benefiting from its efficient training methodology and substantial parameter count. Its 32K context window allows for processing longer inputs and generating more coherent, extended outputs.