Instructions to use spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit 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("spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit")

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 spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit"

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": "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit"

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 "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit" \
  --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 spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit 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 "spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit"

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 spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit

Run Hermes

hermes

Such a good model. 2.6 was the perfect size

by layer4down - opened Jun 29

Discussion

layer4down

Jun 29

Ran this my on M2 Ultra 192GB and it's been so good. Just like 27b but kinda smarter despite being an MoE because of it's vast knowledge. 27b might reason better but this model just feels a bit more capable. Well done.

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