Instructions to use TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ", device_map="auto")
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 Settings

vLLM

How to use TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ",
		"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/TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ

SGLang

How to use TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ 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 "TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ" \
    --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": "TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ",
		"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 "TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ" \
        --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": "TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ",
		"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 TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ with Docker Model Runner:
```
docker model run hf.co/TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ
```

Qwen3.8-Queen-27B-W4A16-AWQ

W4A16 (4-bit weights, 16-bit activations) AWQ compressed-tensors quantization of aifeifei798/Qwen3.8-Queen-27B.

Quantization method

Scheme: W4A16_ASYM — 4-bit asymmetric per-group quantization (group size 128) of all Linear weights, stored in the compressed-tensors pack-quantized format (weight_packed / weight_scale / weight_zero_point / weight_shape), which LMDeploy turbomind auto-detects and loads natively (including the MTP heads and vision tower, which stay BF16).
Tooling: llmcompressor one-shot offline quantization with CPU offloading (compressed_tensors.offload.load_offloaded_model), so the full-precision source fits on a 2×16 GB VRAM setup.
AWQ activation smoothing: AWQModifier with the layer-scoped hybrid-attention mappings from build_hybrid_attention_mappings — full-attention input_layernorm → self_attn.q/k/v, post_attention_layernorm → mlp.gate/up, and mlp.up_proj → mlp.down_proj, with duo_scaling="both" and CPU offload, followed by W4A16 quantization. This layer-scoped recipe is required for hybrid-attention (Qwen3.5-family) architectures — grouped-regex smoothing or mismatched mappings corrupt decoding.
Unquantized (kept BF16): embeddings, lm_head, norms, linear_attn.in_proj_a/b, the vision tower, and MTP heads.

Usage

Tested with LMDeploy turbomind:

from lmdeploy import pipeline, TurbomindEngineConfig

pipe = pipeline(
    "TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ",
    backend_config=TurbomindEngineConfig(
        tp=2,
        model_format="compressed-tensors",
        language_model_only=True,
        cpu_realtime_conversion=True,
    ),
)
print(pipe("Hello, who are you?").text)

Files

quantize-awq-hybrid.py — the script used to produce this quantization (CPU-offloaded, DDP/torchrun, produces properly numbered -of-N shards). --offload_dir selects where per-rank CPU offload temp folders live (defaults to the current working directory).
model-nonquant.safetensors — unquantized tensors (mtp.* and model.visual.*) preserved BF16 so the full model architecture is loadable.

Downloads last month: 12

Safetensors

Model size

28B params

Tensor type

I32

BF16

Model tree for TheUnderscore/Qwen3.8-Queen-27B-W4A16-AWQ

Base model

Qwen/Qwen3.8-27B

Finetuned

aifeifei798/Qwen3.8-Queen-27B

Quantized

(9)

this model