Instructions to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF 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 Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF 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 Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF to start chatting

How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

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 Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

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 "Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

ThinkingCap: Qwen 3.6 27B - MTP GGUF

This is a GGUF quantized version of bottlecapai/ThinkingCap-Qwen3.6-27B customized with MTP (Multi-Token Prediction) support. This repository contains the Q4_K_M quantization, providing a balanced trade-off between memory efficiency and reasoning quality for local inference. By integrating MTP, this specific GGUF model not only thinks with fewer tokens but also generates them significantly faster in compatible runtimes.

⚡ MTP (Multi-Token Prediction) Support

This model is compiled with MTP routing. MTP allows the model to predict multiple future tokens simultaneously during inference rather than one by one. When paired with ThinkingCap's already reduced reasoning trace lengths, this results in blistering fast time-to-first-answer and overall generation speeds on local hardware.

Running with llama.cpp

To take advantage of MTP, ensure you are using a recent build of llama.cpp that supports Qwen's multi-token routing.

(Note: Depending on your specific llama.cpp version, MTP may be enabled by default for supported architectures, or you may need to pass specific draft/speculative flags).

# Basic run command
./llama-cli -hf Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF -p "Explain quantum computing in simple terms."

Downloads last month: 1,785

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Abiray/ThinkingCap-Qwen3.6-27B-MTP-Q4_K_M-GGUF

Base model

Qwen/Qwen3.6-27B

Finetuned

bottlecapai/ThinkingCap-Qwen3.6-27B

Quantized

(46)

this model