Rev3auth/iris

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Sep 11, 2026Architecture:Transformer0.0K Featherless Exclusive Cold

Rev3auth/iris is a 0.3 billion parameter instruction-tuned language model, based on the Gemma architecture, that has been fine-tuned and converted to GGUF format using Unsloth. This compact model is optimized for efficient deployment and inference, making it suitable for applications requiring a small footprint. It is designed for general text-based tasks and includes an Ollama Modelfile for easy integration.

Loading preview...

Overview

Rev3auth/iris is a compact 0.3 billion parameter instruction-tuned language model, specifically the gemma-3-270m-it variant, which has been fine-tuned and converted into the GGUF format. This model leverages Unsloth for its finetuning and conversion process, enabling faster training and efficient deployment.

Key Capabilities

  • GGUF Format: Provided in GGUF format, making it compatible with various inference engines like llama-cpp and ollama.
  • Efficient Training: Benefits from Unsloth's optimizations, allowing for significantly faster training times.
  • Ollama Integration: Includes a pre-configured Ollama Modelfile for straightforward deployment and use within the Ollama ecosystem.
  • Instruction-Tuned: Designed to follow instructions for various text-based tasks.

Good For

  • Local Inference: Ideal for running on consumer-grade hardware due to its small size and GGUF format.
  • Rapid Prototyping: Its ease of deployment with Ollama and compact nature make it suitable for quick development cycles.
  • Resource-Constrained Environments: A strong candidate for applications where computational resources are limited.
  • General Text Generation: Capable of handling a range of text-only LLM tasks.