Instructions to use Qwen/Qwen3.8-27B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3.8-27B-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Qwen/Qwen3.8-27B-FP8")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Qwen/Qwen3.8-27B-FP8")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.8-27B-FP8", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3.8-27B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3.8-27B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen3.8-27B-FP8",
		"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/Qwen/Qwen3.8-27B-FP8

SGLang

How to use Qwen/Qwen3.8-27B-FP8 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 "Qwen/Qwen3.8-27B-FP8" \
    --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": "Qwen/Qwen3.8-27B-FP8",
		"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 "Qwen/Qwen3.8-27B-FP8" \
        --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": "Qwen/Qwen3.8-27B-FP8",
		"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 Qwen/Qwen3.8-27B-FP8 with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3.8-27B-FP8
```

Exploring ThinkingCap fine-tunes for Qwen 3.8: Is it still necessary with native reasoning_effort?

#12

by icognito - opened Aug 16

Discussion

icognito

Aug 16

Hi everyone,

With the recent release of Qwen 3.8 27B, I’ve been reflecting on the impact of models like Bottle Cap AI’s ThinkingCap-Qwen3.6-27B. That fine-tune did a fantastic job of reducing unnecessary Chain-of-Thought (CoT) overthinking by ~50% without dropping reasoning quality.

Now that Qwen 3.8 introduces native reasoning_effort control (low, medium, xhigh, none) directly out of the box, I wanted to open a discussion with the community:

Native Controls vs. Fine-tunes: Does Qwen 3.8’s built-in low or medium reasoning setting solve the overthinking issue effectively, or is there still a strong case for community-driven "ThinkingCap" style fine-tunes?
Efficiency & Speed: How does Qwen 3.8’s native CoT token consumption compare to 3.6 fine-tunes in local setups (vLLM / Ollama / Unsloth)?
Use-case Trade-offs: Are you noticing any drop in complex multi-step coding/math performance when dialing down the reasoning effort on 3.8?

Would love to hear thoughts, benchmark results, or early testing experiences from anyone experimenting with Qwen 3.8 27B!

simpleDoIt

Aug 21

•

edited Aug 21

For me with Qwenn 3.8 27B i have really hard overthinking and looping issues compared to other models, but i have to experiment more with it. So I actually guess a thinking cap model would be really nice.

Jimmy-O

Aug 29

The point of Bottlecap Ais fine tune, was too reach the same answer with less tokens. So In my mind the logic would apply like this:
They make a finetune, that's set to xhigh, but it uses 50 % less tokens, equavalent to the default medium, but with the xhigh result. I don't think in the default model that's the case

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment