Instructions to use TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 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("TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8")
config = load_config("TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8")

# 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

Unsloth Studio

How to use TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8",
    max_seq_length=2048,
)

How to use TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8"

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": "TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8 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 "TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8"

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 TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8

Run Hermes

hermes

Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking

Quality: quantized (mxfp8, group size: 32, 8.341 bpw)

40 billion parameters (dense, not moe) expanded from Qwen3.5 27B, then trained on Claude 4.6 Opus High Reasoning dataset via Unsloth on local hardware.

96 layers, 1275 Tensors. (50% more than base model of 27B)

Features variable length reasoning ; less complex = shorter, longer for more complex.

Model performance has increased dramatically.

256K context.

More information

Source

This model was converted to MLX format from DavidAU/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking using mlx-vlm version 0.4.

Downloads last month: 27

Safetensors

Model size

39B params

Tensor type

U32

BF16

MLX

Hardware compatibility

8-bit

Model tree for TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8

Base model

Qwen/Qwen3.5-27B

Finetuned

DavidAU/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking

Quantized

(10)

this model