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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RDson/Qwen3.6-27B-MTP-Q4_K_M-GGUF",
	filename="Qwen3.6-27B-MTP-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

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

Install from brew

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

Use Docker

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

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

Unsloth Studio new

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

Pi new

How to use RDson/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-server -hf RDson/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": "Qwen3.6-27B-MTP-Q4_K_M-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Qwen3.6-27B-MTP - Q4_K_M GGUF

You currently need to run this with the ikawrakow/ik_llama.cpp fork (main branch, which includes PR ik_llama.cpp for Qwen MTP support).

This was made from Q8_0 and not directly from fp16, some accuracy might been lost due to that.

This is a Q4_K_M GGUF quantization of Qwen3.6-27B that preserves the MTP (Multi-Token Prediction) layers, allowing for significantly faster text generation via speculative decoding.

Standard GGUF conversions often strip out MTP tensors to save a tiny bit of space. This model was carefully requantized fromRadamanthys11/Qwen3.6-27B-MTP-Q8_0-GGUF using ik_llama.cpp to retain the MTP head while shrinking the VRAM requirements down to a highly efficient Q4 footprint.

Performance & Benchmarks

Retaining the MTP layers provides a nearly "free" ~20% generation speedup with zero quality degradation.

Speed Benchmarks:

MTP Off: 26.32 tokens / second
MTP On (--draft-max 1): 31.69 tokens / second (~20% speedup) (Note: Higher draft max than 1 on this specific model decreases t/s for me.

Perplexity:

Dataset: wiki.test.raw
Context: 512
Result: 7.0291 +/- 0.04648 (over 580 chunks)

How to Use

When running your server or CLI, you must pass the MTP flags: -mtp --draft-max 1 --draft-p-min 0.0.

Example Server Command:

./llama-server \
  -m ./Qwen3.6-27B-MTP-Q4_K_M.gguf \
  -c 32768 \
  -mtp --draft-max 1 --draft-p-min 0.0

Creation Details

This file was created using llama-quantize built from ik_llama.cpp using the following command:

./llama-quantize --allow-requantize /path/to/Qwen3.6-27B-MTP-Q8_0.gguf /path/to/Qwen3.6-27B-MTP-Q4_K_M.gguf Q4_K_M

Downloads last month: 2,346

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 RDson/Qwen3.6-27B-MTP-Q4_K_M-GGUF

Base model

Qwen/Qwen3.6-27B

Quantized

(274)

this model