Instructions to use North-ML1/Qwen3.8-Smol-uo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use North-ML1/Qwen3.8-Smol-uo with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("North-ML1/Qwen3.8-Smol-uo")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use North-ML1/Qwen3.8-Smol-uo with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "North-ML1/Qwen3.8-Smol-uo"

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": "North-ML1/Qwen3.8-Smol-uo"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use North-ML1/Qwen3.8-Smol-uo with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "North-ML1/Qwen3.8-Smol-uo"

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 "North-ML1/Qwen3.8-Smol-uo" \
  --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"

MLX LM

How to use North-ML1/Qwen3.8-Smol-uo with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "North-ML1/Qwen3.8-Smol-uo"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "North-ML1/Qwen3.8-Smol-uo"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "North-ML1/Qwen3.8-Smol-uo",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use North-ML1/Qwen3.8-Smol-uo 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 "North-ML1/Qwen3.8-Smol-uo"

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 North-ML1/Qwen3.8-Smol-uo

Run Hermes

hermes

Qwen team, if you need me to change the name or initate deletion, talk in the Community tab.

Qwen3.8-Smol-uo

An MLX LoRA fine-tune of Qwen/Qwen3.5-0.8B on the r0b0tlab/qwen3.8-max-distillation-50k dataset.

This repository contains the converted MLX base model and the final LoRA adapter. It is intended for Apple Silicon with mlx-lm.

Quick start

pip install mlx-lm
hf download North-ML1/Qwen3.8-Smol-uo --local-dir ./Qwen3.8-Smol-uo
mlx_lm.generate \
  --model ./Qwen3.8-Smol-uo \
  --adapter-path ./Qwen3.8-Smol-uo \
  --prompt "Explain gradient accumulation in one sentence." \
  --max-tokens 80

The adapter was trained with four LoRA layers, rank 8, scale 16, a maximum sequence length of 512, and 400 continuation steps from a saved step-100 checkpoint. Final test loss was 0.820 (perplexity 2.271).

This is an MLX-format text model and is not a Transformers/PyTorch checkpoint.

Downloads last month: 1,153

Safetensors

Model size

0.8B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for North-ML1/Qwen3.8-Smol-uo

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Adapter

(186)

this model