Instructions to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF",
	filename="Qwen3.6-27B-MTP-Q3_K_S.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S
# Run inference directly in the terminal:
./llama-cli -hf sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

Use Docker

docker model run hf.co/sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

LM Studio
Jan

vLLM

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

Ollama
How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with Ollama:
```
ollama run hf.co/sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S
```

Unsloth Studio

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF to start chatting

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

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": "sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

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 "sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S" \
  --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 sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with Docker Model Runner:
```
docker model run hf.co/sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S
```

Lemonade

How to use sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF:Q3_K_S

Run and chat with the model

lemonade run user.Qwen3.6-27B-MTP-Q3_K_S-GGUF-Q3_K_S

List all available models

lemonade list

Qwen3.6-27B-MTP Q3_K_S GGUF

This is a plain Q3_K_S GGUF quantization of Qwen3.6-27B that preserves the MTP (Multi-Token Prediction) tensors from Radamanthys11/Qwen3.6-27B-MTP-Q8_0-GGUF. It was requantized from the Q8_0 GGUF source with ik_llama.cpp using --allow-requantize.

Requirements

Use ik_llama.cpp for inference. Pass MTP flags to use speculative decoding:

llama-server -m Qwen3.6-27B-MTP-Q3_K_S.gguf -mtp --draft-max 1 --draft-p-min 0.0

Quantization Recipe

This quant was made from Q8_0 rather than directly from fp16, so a small amount of accuracy may have been lost before this Q3_K_S pass. No imatrix was generated or used for this normal K-quant.

custom="blk\.64\..*\.weight=q8_0,blk\..*\.ssm_alpha\.weight=q6_0,blk\..*\.ssm_beta\.weight=q6_0,blk\..*\.ssm_out\.weight=q6_0,token_embd\.weight=q6_0,output\.weight=q8_0"

./ik_llama.cpp/build/bin/llama-quantize \
  --allow-requantize \
  --custom-q "$custom" \
  ./Qwen3.6-27B-MTP-Q8_0.gguf \
  ./Qwen3.6-27B-MTP-Q3_K_S.gguf \
  Q3_K_S 16

Custom tensor overrides:

blk.64.*.weight MTP/nextn tensors: Q8_0
ssm_alpha.weight, ssm_beta.weight, and ssm_out.weight: Q6_0
token embeddings: Q6_0
output tensor: Q8_0
normal repeating tensors: global Q3_K_S

Source

Source Q8_0 GGUF: Radamanthys11/Qwen3.6-27B-MTP-Q8_0-GGUF

Downloads last month: 127

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

3-bit

Model tree for sandeshrajx/Qwen3.6-27B-MTP-Q3_K_S-GGUF

Base model

Qwen/Qwen3.6-27B

Quantized

(607)

this model