Instructions to use Intel/Qwen3.8-27B-q4km-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Intel/Qwen3.8-27B-q4km-AutoRound 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 Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M # Run inference directly in the terminal: llama cli -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M # Run inference directly in the terminal: llama cli -hf Intel/Qwen3.8-27B-q4km-AutoRound: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 Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Intel/Qwen3.8-27B-q4km-AutoRound: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 Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
Use Docker
docker model run hf.co/Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Intel/Qwen3.8-27B-q4km-AutoRound with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Intel/Qwen3.8-27B-q4km-AutoRound" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Intel/Qwen3.8-27B-q4km-AutoRound", "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/Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
- Ollama
How to use Intel/Qwen3.8-27B-q4km-AutoRound with Ollama:
ollama run hf.co/Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
- Unsloth Studio
How to use Intel/Qwen3.8-27B-q4km-AutoRound 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 Intel/Qwen3.8-27B-q4km-AutoRound 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 Intel/Qwen3.8-27B-q4km-AutoRound to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Intel/Qwen3.8-27B-q4km-AutoRound to start chatting
- Pi
How to use Intel/Qwen3.8-27B-q4km-AutoRound with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Intel/Qwen3.8-27B-q4km-AutoRound: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": "Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Intel/Qwen3.8-27B-q4km-AutoRound with Docker Model Runner:
docker model run hf.co/Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
- Lemonade
How to use Intel/Qwen3.8-27B-q4km-AutoRound with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
Run and chat with the model
lemonade run user.Qwen3.8-27B-q4km-AutoRound-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Intel/Qwen3.8-27B-q4km-AutoRound with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Intel/Qwen3.8-27B-q4km-AutoRound: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 Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Intel/Qwen3.8-27B-q4km-AutoRound with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M
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 "Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M" \ --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"
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M# Run inference directly in the terminal:
llama cli -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_MUse 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 Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_MBuild 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 Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_MUse Docker
docker model run hf.co/Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_MModel Details
This model is a gguf q4km format of Qwen/Qwen3.8-27B generated by intel/auto-round algorithm using best recipe. Please refer to Section Generate the model for more details.
Please follow the license of the original model.
How To Use
Llama.cpp inference.
wget https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg
./llama-cli -m Intel/Qwen3.8-27B-q4km-AutoRound/Qwen3.8-27B-Q4_K_M.gguf -mm Intel/Qwen3.8-27B-q4km-AutoRound/mmproj-model.gguf
> /image demo.jpeg
Loaded media from 'demo.jpeg'
> Describe this image.
[Start thinking]
The user wants a description of the image. The request is in English, so I'll respond in English. Let me carefully observe the image to capture all relevant details.
Subject: A woman and a dog on a beach.
The dog: A light-colored Labrador Retriever (yellow/golden lab), sitting on the sand. It's wearing a harness—blue with some pattern (looks like paw prints or colorful dots) and a red/maroon strap or leash attached. The dog is extending one front paw upward, touching the woman's hand, as if giving a "high five" or "shake."
The woman: Sitting on the sand with her legs bent/crossed. She has long dark hair. She's wearing a plaid/checkered shirt (white and dark, rolled-up sleeves) and dark pants/jeans rolled up. She's barefoot. She has a white watch or band on her wrist. She's smiling, looking at the dog, with one hand raised meeting the dog's paw and the other hand near her lap.
Setting: A sandy beach. In the background, the ocean with a small wave breaking. The horizon line is visible. The sky is bright, washed out, suggesting sunrise or sunset (golden hour). There's a warm golden light/flare on the right side of the image, hitting the woman's hair and the sand, giving a backlit, glowing effect.
Mood: Warm, joyful, peaceful, companionship.
Composition: The two subjects are centered, low in the frame, with lots of negative space (sky and sea) above. The lighting creates a soft, dreamy atmosphere.
Let me write a coherent, vivid description. I'll structure it logically: overall scene, then the dog, then the woman, then the setting and lighting/mood.
I should keep it natural and flowing, not too listy. Final answer in English.
[End thinking]
This image captures a warm, tender moment between a woman and her dog on a sandy beach during the golden hour, likely at sunrise or sunset.
In the center of the frame, a light golden-yellow Labrador Retriever sits upright on the sand, facing right. The dog wears a blue harness decorated with a small colorful pattern (resembling paw prints) and a reddish strap or leash trailing onto the ground behind it. The dog has lifted one front paw and is pressing it gently into the woman's open palm, as if sharing a "high five" or a paw shake.
Beside the dog, a young woman sits on the sand with her legs bent and tucked to one side. She has long, dark hair that glows with a warm halo of light from the low sun. She is dressed casually in a black-and-white checkered (plaid) shirt with the sleeves rolled up, dark pants rolled to the calf, and she is barefoot. A white watch or band is visible on her wrist. She is smiling softly, her gaze fixed on the dog, one hand raised to meet the dog's paw and the other resting near her lap.
The background is a calm sea with a small, soft wave breaking near the shore, and a faint horizon line separates the water from a bright, almost white sky. The lighting is the defining feature of the photo: a strong, warm sun flare enters from the right, washing the scene in honey-gold tones, backlighting the woman's hair and rimming the edges of the sand with light. The overall mood is peaceful, joyful, and affectionate, emphasizing the bond between the woman and her pet against the serene coastal backdrop.
Generate the model
Here is the sample command to reproduce the model
auto_round_best Qwen/Qwen3.8-27B --format "gguf:q4_k_m" --output_dir tmp_autoround --enable_alg_ext
Ethical Considerations and Limitations
The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Therefore, before deploying any applications of the model, developers should perform safety testing.
Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
Citation
@article{cheng2025signroundv2,
title={SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs},
author={Cheng, Wenhua and Zhang, Weiwei and Guo, Heng and Shen, Haihao and Ma, Zaner},
journal={arXiv preprint arXiv:2512.04746},
year={2025}
}
- Downloads last month
- 246
4-bit
Model tree for Intel/Qwen3.8-27B-q4km-AutoRound
Base model
Qwen/Qwen3.8-27B
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M# Run inference directly in the terminal: llama cli -hf Intel/Qwen3.8-27B-q4km-AutoRound:Q4_K_M