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)

# 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=40)
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
```

FP8 KV Cache Calibration

#10

by peterdab - opened 29 days ago

Discussion

peterdab

29 days ago

Hi There,

Great work - Any chance of getting FP8 KV cache calibration to make sure it's possible to use:
--kv-cache-dtype fp8
options safely without VLLM warnings?
Till now I think only unsloth done this here: https://unsloth.ai/docs/models/qwen3.8#nvfp4
I'm looking for the KV cache calibration because of this VLLM article: https://vllm.ai/blog/2026-04-22-fp8-kvcache

Once again 👍

alex81k

24 days ago

•

edited 24 days ago

I have 200+ coding sessions from pi.dev and omp.sh and created custom kv cache calibration. But the most of them were created without reasoning (for Qwen 3.6 27B) so it looks like they're not relevant to 3.8 now :(
But I can share creation workflow so you can try on your own sessions data. There are caveats with config and MTP.

peterdab

24 days ago

I have 200+ coding sessions from pi.dev and omp.sh and created custom kv cache calibration. But the most of them were created without reasoning (for Qwen 3.6 27B) so it looks like they're not relevant to 3.8 now :(
But I can share creation workflow so you can try on your own sessions data. There are caveats with config and MTP.

Hi @alex81k please do.

alex81k

21 days ago

I have 200+ coding sessions from pi.dev and omp.sh and created custom kv cache calibration. But the most of them were created without reasoning (for Qwen 3.6 27B) so it looks like they're not relevant to 3.8 now :(
But I can share creation workflow so you can try on your own sessions data. There are caveats with config and MTP.

Hi @alex81k please do.

Hi @peterdab . Finally I found some time to fix scripts for 3.8: https://github.com/kryoz/4090-48gb-vllm-fp8/tree/main/calibration

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