Rev3auth/iris_16bit

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Sep 12, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Rev3auth/iris_16bit is a 0.3 billion parameter instruction-tuned language model developed by Rev3auth, finetuned from unsloth/gemma-3-270m-it. This model leverages Unsloth for accelerated training, achieving 2x faster finetuning. With a context length of 32768 tokens, it is designed for efficient processing of longer sequences. Its primary differentiator is its optimized training process, making it suitable for applications requiring a compact yet capable model with efficient deployment.

Loading preview...

Model Overview

Rev3auth/iris_16bit is a compact, instruction-tuned language model developed by Rev3auth. It is based on the unsloth/gemma-3-270m-it architecture and features 0.3 billion parameters with a substantial context length of 32768 tokens. This model was finetuned using the Unsloth library in conjunction with Hugging Face's TRL library, which enabled a 2x speedup in the training process.

Key Characteristics

  • Base Model: Finetuned from unsloth/gemma-3-270m-it.
  • Parameter Count: 0.3 billion parameters, offering a balance between performance and efficiency.
  • Context Length: Supports a context window of 32768 tokens, suitable for processing longer inputs.
  • Optimized Training: Utilizes Unsloth for significantly faster finetuning, reducing development time and computational resources.

Ideal Use Cases

This model is well-suited for developers looking for:

  • Efficient Deployment: Its smaller size makes it easier to deploy in resource-constrained environments.
  • Rapid Prototyping: The accelerated training process allows for quicker iteration and experimentation.
  • Applications Requiring Longer Context: The 32768 token context window is beneficial for tasks involving extensive text analysis or generation.