---
title: K2-Horizon-7B-Uno-oQ6e
canonical_url: "https://www.modelscope.cn/models/mlx-community/K2-Horizon-7B-Uno-oQ6e"
md_url: "https://www.modelscope.cn/models/mlx-community/K2-Horizon-7B-Uno-oQ6e.md"
repository: mlx-community/K2-Horizon-7B-Uno-oQ6e
last_updated: 2026-09-11
license: apache-2.0
model_type:
  - k2_horizon
architectures:
  - K2HorizonForCausalLM
base_model:
  - IFM/K2-Horizon-7B-Uno
base_model_relation: quantized
parameters: 2.0B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 21
stars: 0
tags:
  - mlx
  - apple-silicon
  - text-generation
  - uno
  - oQ
  - oQ6e
---

# K2-Horizon-7B-Uno-oQ6e

> K2-Horizon-7B-Uno-oQ6e - mlx-community 在 ModelScope 开源的模型。K2-Horizon-7B-Uno oQ6e

mlx-community/K2-Horizon-7B-Uno-oQ6e 是 ModelScope 魔搭社区上的 2.0B 参数机器学习模型，采用 apache-2.0 许可，基于 IFM/K2-Horizon-7B-Uno 构建。

- **Repository**: mlx-community/K2-Horizon-7B-Uno-oQ6e
- **License**: apache-2.0
- **Parameters**: 2.0B
- **Base model**: IFM/K2-Horizon-7B-Uno
- **Tags**: mlx, apple-silicon, text-generation, uno, oQ, oQ6e
- **Downloads**: 21
- **Stars**: 0
- **Last updated**: 2026-09-11

Source: https://www.modelscope.cn/models/mlx-community/K2-Horizon-7B-Uno-oQ6e

---

# K2-Horizon-7B-Uno oQ6e

oQ6e (imatrix-enhanced mixed-precision ~6.5 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-oQ6e \
  --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-oQ6e",
    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).