Instructions to use iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP 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("iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP")
config = load_config("iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP")

# 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 iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP"

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": "iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP 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 "iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP"

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 iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP"

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 "iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP" \
  --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"

Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

Added full MTP support, KV Quantization Merged jinja chat template fix from froggeric/Qwen-Fixed-Chat-Templates

Instructions

You will need this branch of mlx-lm:

https://github.com/iamthecage/mlx-lm

Install mlx-lm from the cloned repo:

pip install -e . --no-build-isolation

Optional(highly recommended): Install OptiQ to enable KV Quantization and fused SPDA optimizations

pip install mlx-optiq

Serve with:

mlx_lm.server \                                 
  --model iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP \
  --mtp-draft --num-draft-tokens 4 \
  --kv-bits 8 --kv-group-size 64 --quantized-kv-start 2048 \
  --chat-template-args '{"enable_thinking": true, "preserve_thinking": true, "auto_disable_thinking_with_tools": true}' \
  --temp 0 --host 127.0.0.1 --port 8082

MTP Enabled INFO - Metrics: prompt 23123 tok @ 318.8 tok/s | gen 157 tok @ 20.2 tok/s | peak 34.22 GB | mtp 116/157 accepted (74%) accept-len 3.83

MTP Disabled INFO - Metrics: prompt 28152 tok @ 362.8 tok/s | gen 144 tok @ 9.8 tok/s | peak 34.22 GB

Quality: quantized (mixed quants per tensor, group size: 32, 7.652 bpw)

Most tensors use 6-bit or 8-bit affine quantization with a group size 32.

Fully uncensored and then fine-tuned by DavidAU.

Abliteration metrics

Metric	This model	Original model (unsloth/Qwen3.6-27B)
KL divergence	0.0469	0 (by definition)
Refusals	4/100	99/100

IN HOUSE BENCHMARKS [by Nightmedia]:
         arc-c arc/e boolq hswag obkqa piqa  wino
Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
mxfp8    0.673,0.846,0.905... [instruct mode]
Qwen3.6-27B-Heretic-Uncensored-Finetune-Thinking
mxfp8    0.669,0.835,0.906,...   [instruct mode]
---
BASE UNTUNED MODEL:
Qwen3.6-27B HERETIC (by llmfan46) [instruct mode]
mxfp8    0.644,0.788,0.902,...
Qwen3.6-27B (by Qwen) [instruct mode]
mxfp8    0.647,0.803,0.910,0.773,0.450,0.806,0.742

Source

This model was converted to MLX format from DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking using mlx-vlm version 0.4.4.

Downloads last month: 48

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

8-bit

Model tree for iamthecage/Qwen3.6-27B-Thinking-MLX-mixed-7.6bit-MTP

Base model

trohrbaugh/Qwen3.6-27B-heretic-ara

Finetuned

DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

Quantized

(21)

this model