Ornith-1.0-9B-GGUF

Direct GGUF Quantizations of Ornith-1.0-9B

This repository provides GGUF quantized models for deepreinforce-ai/Ornith-1.0-9B.

Ornith-1.0-9B is the most lightweight member of the Ornith-1.0 family, a self-improving open-source model family for agentic coding developed by DeepReinforce. Built on top of Qwen 3.5, it is a dense ~9B reasoning model (≈19 GB in bf16) that achieves state-of-the-art performance among open-source models of comparable size on coding benchmarks including Terminal-Bench 2.1, SWE-Bench Verified (69.4%), SWE-Bench Pro, NL2Repo, and ClawEval. It supports tool-calling, emits structured <think> … </think> reasoning traces, and is optimized for terminal-based coding agents and agentic workflows. These GGUF versions enable efficient local inference via llama.cpp and compatible tools.

This release includes various quantization levels (e.g., Q2_K, Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0) to suit different hardware and performance requirements. Q4_K_M is the recommended sweet spot for most setups; use Q6_K or Q8_0 for maximum fidelity.

⚠️ Important: Always pass --jinja when loading with llama.cpp so the Ornith-1.0-9B chat template is applied correctly. Without it, the model may emit malformed turns.

Table of Contents 📝

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

pip install "huggingface_hub[cli]"
huggingface-cli download samuelchristlie/Ornith-1.0-9B-gguf --local-dir ./Ornith-1.0-9B-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 a llama.cpp backend).

Recommended sampling parameters: temperature=0.6, top_p=0.95, top_k=20. Use temperature=1.0 to reproduce the original published benchmark results.

llama.cpp (server)

llama-server -hf samuelchristlie/Ornith-1.0-9B-gguf --port 8000 -c 262144 --jinja

Ollama

ollama run hf.co/samuelchristlie/Ornith-1.0-9B-gguf

Parsing Reasoning Traces

Ornith-1.0-9B is a reasoning model — responses begin with a <think> … </think> block containing the chain-of-thought, followed by the final answer. To split them:

if "</think>" in text:
    reasoning, answer = text.split("</think>", 1)
    reasoning = reasoning.replace("<think>", "").strip()
    answer = answer.strip()
else:
    reasoning, answer = "", text.strip()