Instructions to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="guili9300/Qwopus3.6-27B-v1-preview-GGUF",
	filename="Qwopus3.6-27B-v1-preview-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf guili9300/Qwopus3.6-27B-v1-preview-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 guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf guili9300/Qwopus3.6-27B-v1-preview-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 guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf guili9300/Qwopus3.6-27B-v1-preview-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 guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M

Use Docker

docker model run hf.co/guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "guili9300/Qwopus3.6-27B-v1-preview-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": "guili9300/Qwopus3.6-27B-v1-preview-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M

Ollama
How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with Ollama:
```
ollama run hf.co/guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M
```

Unsloth Studio

How to use guili9300/Qwopus3.6-27B-v1-preview-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 guili9300/Qwopus3.6-27B-v1-preview-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 guili9300/Qwopus3.6-27B-v1-preview-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for guili9300/Qwopus3.6-27B-v1-preview-GGUF to start chatting

How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf guili9300/Qwopus3.6-27B-v1-preview-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": "guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf guili9300/Qwopus3.6-27B-v1-preview-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 guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with Docker Model Runner:
```
docker model run hf.co/guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M
```

Lemonade

How to use guili9300/Qwopus3.6-27B-v1-preview-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull guili9300/Qwopus3.6-27B-v1-preview-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwopus3.6-27B-v1-preview-GGUF-Q4_K_M

List all available models

lemonade list

Qwopus3.6-27B-v1-preview - GGUF

This repository contains GGUF quantized formats of Jackrong/Qwopus3.6-27B-v1-preview.

Qwopus3.6-27B-v1-preview is an early preview reasoning model built on top of the Qwen3.6-27B multimodal base. It is heavily fine-tuned to deliver stronger reasoning quality, a stable answer structure, and more consistent long-form responses. It defaults to a "thinking" mode where reasoning is generated inside <think>...</think> tags prior to the final response.

Available Quantizations

The following quantization formats are provided to balance VRAM/RAM usage and model performance:

File Name	Quant Type	Description
`Qwopus3.6-27B-v1-preview-Q4_K_M.gguf`	Q4_K_M	Recommended. Excellent balance of quality and size.
`Qwopus3.6-27B-v1-preview-Q4_K_S.gguf`	Q4_K_S	Slightly smaller than Q4_K_M, minor quality trade-off.
`Qwopus3.6-27B-v1-preview-Q5_K_M.gguf`	Q5_K_M	Higher precision. Requires more RAM/VRAM.
`Qwopus3.6-27B-v1-preview-Q5_K_S.gguf`	Q5_K_S	Good balance for those who want Q5 precision with slightly lower memory footprint.
`Qwopus3.6-27B-v1-preview-Q6_K.gguf`	Q6_K	Near-unquantized quality, very large file size.
`Qwopus3.6-27B-v1-preview-Q8_0.gguf`	Q8_0	Highest quality, virtually indistinguishable from FP16.

Prompt Format

This model uses the standard Qwen chat template. By default, it operates in a reasoning mode. The output format generally follows:

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
[Your Prompt Here]<|im_end|>
<|im_start|>assistant
<think>
[Reasoning trace]
</think>
[Final Answer]<|im_end|>

Downloads last month: 106

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for guili9300/Qwopus3.6-27B-v1-preview-GGUF

Base model

Qwen/Qwen3.6-27B

Finetuned

Jackrong/Qwopus3.6-27B-v1-preview

Quantized

(11)

this model