Instructions to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="YTan2000/Qwopus3.6-27B-v2-TQ3_4S",
	filename="Qwopus3.6-27B-v2-TQ3_4S.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

llama.cpp

How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S
# Run inference directly in the terminal:
llama-cli -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S
# Run inference directly in the terminal:
llama-cli -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S

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 YTan2000/Qwopus3.6-27B-v2-TQ3_4S
# Run inference directly in the terminal:
./llama-cli -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S

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 YTan2000/Qwopus3.6-27B-v2-TQ3_4S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S

Use Docker

docker model run hf.co/YTan2000/Qwopus3.6-27B-v2-TQ3_4S

LM Studio
Jan

vLLM

How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YTan2000/Qwopus3.6-27B-v2-TQ3_4S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YTan2000/Qwopus3.6-27B-v2-TQ3_4S",
		"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/YTan2000/Qwopus3.6-27B-v2-TQ3_4S

Ollama
How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with Ollama:
```
ollama run hf.co/YTan2000/Qwopus3.6-27B-v2-TQ3_4S
```

Unsloth Studio new

How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S 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 YTan2000/Qwopus3.6-27B-v2-TQ3_4S 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 YTan2000/Qwopus3.6-27B-v2-TQ3_4S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for YTan2000/Qwopus3.6-27B-v2-TQ3_4S to start chatting

Pi new

How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S

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": "YTan2000/Qwopus3.6-27B-v2-TQ3_4S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf YTan2000/Qwopus3.6-27B-v2-TQ3_4S

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 YTan2000/Qwopus3.6-27B-v2-TQ3_4S

Run Hermes

hermes

Docker Model Runner
How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with Docker Model Runner:
```
docker model run hf.co/YTan2000/Qwopus3.6-27B-v2-TQ3_4S
```

Lemonade

How to use YTan2000/Qwopus3.6-27B-v2-TQ3_4S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YTan2000/Qwopus3.6-27B-v2-TQ3_4S

Run and chat with the model

lemonade run user.Qwopus3.6-27B-v2-TQ3_4S-{{QUANT_TAG}}

List all available models

lemonade list

Qwopus3.6-27B-v2-TQ3_4S

TQ3_4S is a 3.5-bit Walsh-Hadamard-transform weight format with four per-8 scales per 32-weight block.

This repository packages Jackrong/Qwopus3.6-27B-v2 as a TurboQuant TQ3_4S GGUF for local deployment.

Quantization Source

HF source checkout:
- Jackrong/Qwopus3.6-27B-v2
upstream family:
- Qwen/Qwen3.6-27B
F16/BF16 GGUF used as the quantization source:
- Qwopus3.6-27B-v2-f16.gguf or the converted BF16 source used by llama-quantize

Quantized with:

./build/bin/llama-quantize --pure \
  /path/to/Qwopus3.6-27B-v2-f16.gguf \
  /path/to/Qwopus3.6-27B-v2-TQ3_4S.gguf \
  TQ3_4S \
  16

Runtime Validation

Validated on a TurboQuant-capable llama.cpp build.

Example server settings:

llama-server \
  -m Qwopus3.6-27B-v2-TQ3_4S.gguf \
  --host 127.0.0.1 --port 8080 \
  -ngl 99 -c 8192 -np 1 \
  -ctk q4_0 -ctv tq3_0 -fa on \
  --jinja --no-cache-prompt --cache-ram 0

Runtime

Native TQ3_4S support requires the turbo-tan/llama.cpp-tq3 fork.

Launch contract: -ngl 99 -c 8192 -np 1 -ctk q4_0 -ctv tq3_0 -fa on
Keep --jinja enabled for the bundled chat template
Use the matching mmproj.gguf for multimodal input

Files

File	Quant	Size
`Qwopus3.6-27B-v2-TQ3_4S.gguf`	TQ3_4S	~13.0 GB
`mmproj.gguf`	multimodal projector	~0.9 GB
`thumbnail.png`	model card image	png
`chat_template.jinja`	chat template	text

Notes

The source repo includes mmproj.gguf in its paired GGUF repository.
Upload mmproj.gguf alongside this model to preserve multimodal packaging.
Keep --jinja enabled so the bundled template is used.
If your frontend says image input is unsupported, it is usually pointing at a server instance that was started without --mmproj.
If native TQ3_4S support is missing, use the turbo-tan/llama.cpp-tq3 fork.