Instructions to use TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit 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/Qwen3.5-35B-A3B-Heretic-MLX-4bit")
config = load_config("TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit")

# 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 TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit 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/Qwen3.5-35B-A3B-Heretic-MLX-4bit"

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": "TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit 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/Qwen3.5-35B-A3B-Heretic-MLX-4bit"

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/Qwen3.5-35B-A3B-Heretic-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit"

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 "TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit" \
  --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"

Qwen3.5-35B-A3B-Heretic-MLX-4bit / README.md

TheCluster

Update README.md

c8eb560 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

3.14 kB

metadata

license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE
language:
  - en
  - zh
base_model:
  - brayniac/Qwen3.5-35B-A3B-heretic
library_name: mlx
tags:
  - heretic
  - uncensored
  - unrestricted
  - decensored
  - abliterated
pipeline_tag: image-text-to-text
new_version: TheCluster/Qwen3.6-35B-A3B-Heretic-MLX-4bit

Qwen3.5-35B-A3B Heretic

Quality: quantized (4 bit affine, group size: 32, 4.649 bpw)

This is an uncensored version of Qwen/Qwen3.5-35B-A3B, made using Heretic v1.2.0

Performance

Metric	This model	Original model (a model)
KL divergence	0.0825	0 (by definition)
Refusals	5/100	92/100

Abliteration parameters

Parameter	Value
direction_index	20.06
linear_attn.out_proj.max_weight	0.93
linear_attn.out_proj.max_weight_position	37.63
linear_attn.out_proj.min_weight	0.71
linear_attn.out_proj.min_weight_distance	4.94
moe_experts.down_proj.max_weight	1.18
moe_experts.down_proj.max_weight_position	23.68
moe_experts.down_proj.min_weight	0.86
moe_experts.down_proj.min_weight_distance	5.48
shared_expert.down_proj.max_weight	1.33
shared_expert.down_proj.max_weight_position	36.08
shared_expert.down_proj.min_weight	0.70
shared_expert.down_proj.min_weight_distance	17.75
attn.o_proj.max_weight	0.83
attn.o_proj.max_weight_position	35.00
attn.o_proj.min_weight	0.06
attn.o_proj.min_weight_distance	15.22

Sampling Parameters:

I suggest using the following sets of sampling parameters depending on the mode and task type:
- Thinking mode for general tasks:
  temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
- Thinking mode for precise coding tasks (e.g., WebDev):
  temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
- Instruct (or non-thinking) mode for general tasks:
  temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
- Instruct (or non-thinking) mode for reasoning tasks:
  temperature=1.0, top_p=1.0, top_k=40, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0
For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.

Source

This model was converted to MLX format from brayniac/Qwen3.5-35B-A3B-heretic using mlx-vlm version 0.3.12.