Instructions to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF",
	filename="Qwen3.5-27B-SGR-LCL-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jeffchanpm/Qwen3.5-27B-SGR-LCL-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 jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jeffchanpm/Qwen3.5-27B-SGR-LCL-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 jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jeffchanpm/Qwen3.5-27B-SGR-LCL-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 jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M

Use Docker

docker model run hf.co/jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeffchanpm/Qwen3.5-27B-SGR-LCL-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": "jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M

Ollama
How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with Ollama:
```
ollama run hf.co/jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M
```

Unsloth Studio new

How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-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 jeffchanpm/Qwen3.5-27B-SGR-LCL-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 jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF to start chatting

Pi new

How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jeffchanpm/Qwen3.5-27B-SGR-LCL-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": "jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-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 jeffchanpm/Qwen3.5-27B-SGR-LCL-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 jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with Docker Model Runner:
```
docker model run hf.co/jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M
```

Lemonade

How to use jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-27B-SGR-LCL-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-27B-SGR-LCL-GGUF

GGUF quantized versions of Qwen3.5-27B-SGR-LCL.

Available Quantizations

File	Quant	Size	BPW	Notes
Qwen3.5-27B-SGR-LCL-Q4_K_M.gguf	Q4_K_M	16 GB	4.92	Recommended for most use cases

About the Model

Fine-tuned from Qwen3.5-27B using Self-Graph Reasoning (SGR) + Logical Curriculum Learning (LCL). Key results:

Thinking mode: +6.5% over baseline (78.0% → 84.5%)
ProverQA Hard: +12.0% in thinking mode
Near-zero skip-think degradation: -1.2%

See the full model card for detailed results and methodology.

Quantization Verification (Q4_K_M vs BF16 LoRA)

Mode	BF16 LoRA	Q4_K_M	Delta
Skip-think (3000 questions)	75.0%	76.2%	+1.2%
Thinking (200 questions)	84.5%	81.5%	-3.0%

Thinking mode delta is within statistical variance (N=50 per dataset, each question = 2% weight).

Usage

llama.cpp / llama-server

# Download
huggingface-cli download jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF \
  Qwen3.5-27B-SGR-LCL-Q4_K_M.gguf --local-dir .

# Serve
llama-server -m Qwen3.5-27B-SGR-LCL-Q4_K_M.gguf -c 4096 -np 1

Ollama

# Create Modelfile
cat > Modelfile << 'EOF'
FROM ./Qwen3.5-27B-SGR-LCL-Q4_K_M.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.8
EOF

ollama create qwen3.5-sgr-lcl -f Modelfile
ollama run qwen3.5-sgr-lcl

Citation

@article{chen2026chains,
  title={From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs},
  author={Chen, Yingjian and Liu, Haoran and Liu, Yinhong and Tong, Sherry T and Feng, Aosong and Lu, Jinghui and Zhang, Juntao and Iwasawa, Yusuke and Matsuo, Yutaka and Li, Irene},
  journal={arXiv preprint arXiv:2601.03597},
  year={2026}
}

Downloads last month: 15

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF

Base model

Qwen/Qwen3.5-27B

Adapter

jeffchanpm/Qwen3.5-27B-SGR-LCL

Quantized

(1)

this model

Paper for jeffchanpm/Qwen3.5-27B-SGR-LCL-GGUF

From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs

Paper • 2601.03597 • Published Jan 7