Instructions to use t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit 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("t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit")
config = load_config("t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit")

# 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 t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit"

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": "t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit 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 "t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit"

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 t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit

Run Hermes

hermes

OpenClaw new

How to use t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit"

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 "t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit" \
  --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"

8-bit MLX quantization of bottlecapai/ThinkingCap-Qwen3.6-27B (Qwen3.6-27B finetuned for ~50% shorter thinking traces). See the original card for evals and recommended sampling params.

Model quantized using mlx_vlm version 0.6.4 at Q8 using:

mlx_vlm.convert \
  --hf-path bottlecapai/ThinkingCap-Qwen3.6-27B \
  --mlx-path ./ThinkingCap-Qwen3.6-27B-mlx-8bit \
  --quantize --q-bits 8

Runs in LM Studio (requires a recent MLX engine with qwen3_5_vision support). Tested on M4 Pro with 48GB.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Model tree for t-prazak/ThinkingCap-Qwen3.6-27B-MLX-8bit

Base model

Qwen/Qwen3.6-27B

Finetuned

bottlecapai/ThinkingCap-Qwen3.6-27B

Quantized

(12)

this model