Image-Text-to-Text
Transformers
Safetensors
qwen3_5
autoround
int4
w4g128
w4a16
quantization
vllm
multimodal
mtp
speculative-decoding
code
coding
conversational
4-bit precision
auto-round
Instructions to use webhie/Qwen3.6-27B-int4-AutoRound-Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="webhie/Qwen3.6-27B-int4-AutoRound-Code") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("webhie/Qwen3.6-27B-int4-AutoRound-Code") model = AutoModelForImageTextToText.from_pretrained("webhie/Qwen3.6-27B-int4-AutoRound-Code") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "webhie/Qwen3.6-27B-int4-AutoRound-Code" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "webhie/Qwen3.6-27B-int4-AutoRound-Code", "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/webhie/Qwen3.6-27B-int4-AutoRound-Code
- SGLang
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "webhie/Qwen3.6-27B-int4-AutoRound-Code" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "webhie/Qwen3.6-27B-int4-AutoRound-Code", "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 images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "webhie/Qwen3.6-27B-int4-AutoRound-Code" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "webhie/Qwen3.6-27B-int4-AutoRound-Code", "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" } } ] } ] }' - Docker Model Runner
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with Docker Model Runner:
docker model run hf.co/webhie/Qwen3.6-27B-int4-AutoRound-Code
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 128, | |
| "sym": true, | |
| "iters": 1000, | |
| "low_gpu_mem_usage": true, | |
| "nsamples": 512, | |
| "autoround_version": "0.13.0", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| "model.language_model.layers.0.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.0.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.1.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.1.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.2.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.2.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.4.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.4.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.5.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.5.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.6.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.6.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.8.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.8.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.9.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.9.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.10.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.10.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.12.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.12.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.13.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.13.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.14.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.14.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.16.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.16.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.17.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.17.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.18.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.18.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.20.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.20.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.21.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.21.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.22.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.22.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.24.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.24.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.25.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.25.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.26.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.26.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.28.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.28.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.29.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.29.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.30.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.30.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.32.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.32.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.33.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.33.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.34.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.34.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.36.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.36.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.37.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.37.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.38.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.38.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.40.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.40.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.41.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.41.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.42.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.42.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.44.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.44.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.45.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.45.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.46.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.46.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.48.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.48.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.49.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.49.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.50.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.50.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.52.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.52.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.53.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.53.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.54.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.54.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.56.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.56.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.57.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.57.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.58.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.58.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.60.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.60.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.61.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.61.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.62.linear_attn.in_proj_b": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.language_model.layers.62.linear_attn.in_proj_a": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| } | |
| } | |
| } |