Instructions to use bearzi/Qwen3-Coder-Next-oQ2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bearzi/Qwen3-Coder-Next-oQ2 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("bearzi/Qwen3-Coder-Next-oQ2")

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 bearzi/Qwen3-Coder-Next-oQ2 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bearzi/Qwen3-Coder-Next-oQ2"

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": "bearzi/Qwen3-Coder-Next-oQ2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use bearzi/Qwen3-Coder-Next-oQ2 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "bearzi/Qwen3-Coder-Next-oQ2"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "bearzi/Qwen3-Coder-Next-oQ2"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "bearzi/Qwen3-Coder-Next-oQ2",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use bearzi/Qwen3-Coder-Next-oQ2 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 "bearzi/Qwen3-Coder-Next-oQ2"

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 bearzi/Qwen3-Coder-Next-oQ2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bearzi/Qwen3-Coder-Next-oQ2 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "bearzi/Qwen3-Coder-Next-oQ2"

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 "bearzi/Qwen3-Coder-Next-oQ2" \
  --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"

Qwen3-Coder-Next-oQ2

oQ2 mixed-precision MLX quantization produced via oMLX.

Quantization: oQ2 (sensitivity-driven mixed precision, group_size=64)
Format: MLX safetensors
Compatible with: mlx-lm, mlx-vlm, oMLX on Apple Silicon

Usage

from mlx_lm import load, generate
model, tokenizer = load("bearzi/Qwen3-Coder-Next-oQ2")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Hello"}],
    add_generation_prompt=True,
)
print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True))

About oQ

oQ measures per-layer quantization sensitivity through calibration and allocates bits where they matter most — critical layers stay at higher precision, tolerant layers compress aggressively. Target averages of 2/3/4/6/8 bits are provided; actual per-layer bits vary by measured sensitivity.

See oQ documentation.

Comparative benchmarks and feedback welcome — please open a discussion.