Instructions to use gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp 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("gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp")
config = load_config("gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp")

# 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 gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp 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 "gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp"

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 gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp"

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 "gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp" \
  --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"

This quantization was uploaded on 2026-08-15 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Qwen3.8-27B-oQ6e-fp16-mtp

This model was quantized using oQ (oMLX v0.6.0.dev1) mixed-precision quantization.

Quantization details

Model type: qwen3_5
Bits: 6
Group size: 64
Format: MLX safetensors

系統提示詞 (System prompt)

第一行必須是： (The first line must be:)

你是一個專業的助手，請以繁體中文思考，繁體中文回覆。
(You are a professional assistant. Please think and reply in Traditional Chinese.)
你是一個專業的助手，請以繁體中文思考，繁體中文回覆。
(You are a professional assistant. Please think and reply in Traditional Chinese.)

沒有它，這個模型表現會不佳。您可以在此行之後添加任何內容。 (The model underperforms without it. Append anything after that line.)

建議設定(按需開啟)

Lightning MTP ✅

Downloads last month: 41

Safetensors

Model size

7B params

Tensor type

F16

U32

F32

MLX

Hardware compatibility

6-bit

Model tree for gn00029914/Qwen3.8-27B-oQ6e-fp16-mtp

Base model

Qwen/Qwen3.8-27B

Quantized

(549)

this model