CoolFace
Modelpublic

samuelchristlie/tmax-9b-gguf

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes3.3kdownloads
Model Card

Tmax-9B-GGUF

Direct GGUF Quantizations of Tmax-9B

This repository provides GGUF quantized models for allenai/tmax-9b.

Tmax-9B is a 9 billion parameter terminal-agent model developed by AllenAI and collaborators. Built on top of the Qwen3.5-9B architecture and further trained using reinforcement learning for terminal-based tasks, it is designed to perform complex command-line and software engineering workflows while maintaining strong general-purpose reasoning capabilities. These GGUF versions are optimized for efficient CPU and GPU inference using llama.cpp and compatible tools.

This release includes various quantization levels (e.g., Q2K, Q3KM, Q4KM, Q5KM, Q6K, Q8_0) to suit different hardware capabilities and performance requirements.

Table of Contents 📝

  1. 1.▶ Usage
  2. 2.📃 License
  3. 3.🙏 Acknowledgements

<a name="usage"/>

▶ Usage

1. Download Models

Download models using huggingface-cli:

bash
pip install "huggingface_hub[cli]"
huggingface-cli download samuelchristlie/tmax-9B-gguf --local-dir ./tmax-9B-gguf

You can also download directly from this page

2. Inference

To use these GGUF files, you'll need a compatible inference engine like llama.cpp or clients built on top of it (e.g., Ollama, LM Studio, KoboldCpp, text-generation-webui with llama.cpp backend).

<a name="license"/>

📃 License

This model is a GGUF conversion of the original allenai/tmax-9b model. The original model is licensed under the Apache 2.0 License, and this derivative work adheres to the terms of that license. Please review the original license for full details.

<a name="acknowledgements"/>

🙏 Acknowledgements

  • —Allen Institute for AI (AI2) and collaborators for developing and open-sourcing the Tmax-9B model:
  • —https://huggingface.co/allenai/tmax-9b
  • —Qwen Team for the Qwen3.5-9B base model that powers Tmax-9B:
  • —https://huggingface.co/Qwen/Qwen3.5-9B
  • —The llama.cpp project and its contributors for the GGUF format and the incredible tooling that makes local LLM inference accessible.
  • —https://github.com/ggml-org/llama.cpp
  • —city96:
  • —https://huggingface.co/city96

</div>