Instructions to use orcarouter/Qwen3.8-27B-Uncensored-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use orcarouter/Qwen3.8-27B-Uncensored-MLX with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("orcarouter/Qwen3.8-27B-Uncensored-MLX")
config = load_config("orcarouter/Qwen3.8-27B-Uncensored-MLX")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use orcarouter/Qwen3.8-27B-Uncensored-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "orcarouter/Qwen3.8-27B-Uncensored-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "orcarouter/Qwen3.8-27B-Uncensored-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use orcarouter/Qwen3.8-27B-Uncensored-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "orcarouter/Qwen3.8-27B-Uncensored-MLX"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default orcarouter/Qwen3.8-27B-Uncensored-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use orcarouter/Qwen3.8-27B-Uncensored-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "orcarouter/Qwen3.8-27B-Uncensored-MLX"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "orcarouter/Qwen3.8-27B-Uncensored-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

无法关闭思考

by itzRomeo - opened Aug 22

Discussion

itzRomeo

Aug 22

我在使用 LM Studio 的时候，加载这个模型并没有给我思考功能开关。请问这是在预期内的吗？

sailorjs0804

OrcaRouter org Aug 23

感谢你的反馈，我已经把模板原样内嵌回 tokenizer_config.json(内容与 chat_template.jinja 逐字节一致)。请重新下载或刷新一下模型,LM Studio 里面就能显示思考开关了

itzRomeo

Aug 24

感谢你的反馈，我已经把模板原样内嵌回 tokenizer_config.json(内容与 chat_template.jinja 逐字节一致)。请重新下载或刷新一下模型,LM Studio 里面就能显示思考开关了

我重新下载了 Tokenizer-config.json 文件。并将我本地模型的文件替换了，并在 LM Studio 里面刷新模型。不过仍然没有看到思考功能开关

sailorjs0804

OrcaRouter org Aug 24

I have fixed it. You can try again and it works fine in my pc

itzRomeo

Aug 24

Maybe I make mistakes.

janxxxxx

28 days ago

Hello, I down the model from Bionic using HF url serveral days ago.
However I found there is still no thinking configuration. Have I done something wrong or I should not download the model in Bionic (download from HF instead) to keep this function operational?
Thanks !

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment