---
base_model: IFM/K2-Horizon-7B-Uno
tags:
  - mlx
  - apple-silicon
  - text-generation
  - uno
  - oQ
  - oQ4e
license: apache-2.0
---

# K2-Horizon-7B-Uno oQ4e

oQ4e (imatrix-enhanced mixed-precision ~4.5 BPW) quantization of the merged [IFM/K2-Horizon-7B-Uno](https://huggingface.co/IFM/K2-Horizon-7B-Uno) model — a diffusion-augmented LLM based on K2-Horizon-7B. The LoRA adapter is baked into the base weights, so it runs as a standard autoregressive model.

**Upstream model:** [IFM/K2-Horizon-7B-Uno](https://huggingface.co/IFM/K2-Horizon-7B-Uno) by Institute of Foundation Models, released under Apache 2.0.

**Conversion:** Merged using PyTorch + PEFT, validated with text generation, then quantized to MLX format using [Hermes Agent](https://hermes-agent.nousresearch.com) with `oMLX`.

## Quickstart

```bash
pip install -U mlx-lm

python3 -m mlx_lm.generate \
  --model hermitdave/K2-Horizon-7B-Uno-oQ4e \
  --prompt "Explain step by step." \
  --max-tokens 512 --temp 1.0 --top-p 0.95
```

## Reasoning

K2-Horizon-7B is a reasoning model. Always use `reasoning_effort="high"`:

```python
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="hermitdave/K2-Horizon-7B-Uno-oQ4e",
    messages=[{"role": "user", "content": "Explain step by step."}],
    extra_body={"chat_template_kwargs": {"reasoning_effort": "high"}},
)
print("Reasoning:", getattr(response.choices[0].message, "reasoning_content", None))
print("Answer:", response.choices[0].message.content)
```

## oMLX Patch

K2-Horizon requires oMLX v0.6.4+ with the [K2-Horizon support patch](https://github.com/jundot/omlx/pull/3441).

## Citation

```bibtex
@misc{k2_horizon_7b_uno,
  title        = {K2-Horizon-7B-Uno},
  author       = {Institute of Foundation Models},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/IFM/K2-Horizon-7B-Uno}},
}
```

## License

Apache 2.0 (same as upstream).