Instructions to use TK-13/Qwen3.8-Flash-Next-FP8-Recreated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TK-13/Qwen3.8-Flash-Next-FP8-Recreated with Transformers:

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

pipe = pipeline("image-text-to-text", model="TK-13/Qwen3.8-Flash-Next-FP8-Recreated")
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("TK-13/Qwen3.8-Flash-Next-FP8-Recreated")
model = AutoModelForMultimodalLM.from_pretrained("TK-13/Qwen3.8-Flash-Next-FP8-Recreated", 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 TK-13/Qwen3.8-Flash-Next-FP8-Recreated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TK-13/Qwen3.8-Flash-Next-FP8-Recreated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TK-13/Qwen3.8-Flash-Next-FP8-Recreated",
		"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/TK-13/Qwen3.8-Flash-Next-FP8-Recreated

SGLang

How to use TK-13/Qwen3.8-Flash-Next-FP8-Recreated 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 "TK-13/Qwen3.8-Flash-Next-FP8-Recreated" \
    --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": "TK-13/Qwen3.8-Flash-Next-FP8-Recreated",
		"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 "TK-13/Qwen3.8-Flash-Next-FP8-Recreated" \
        --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": "TK-13/Qwen3.8-Flash-Next-FP8-Recreated",
		"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 TK-13/Qwen3.8-Flash-Next-FP8-Recreated with Docker Model Runner:
```
docker model run hf.co/TK-13/Qwen3.8-Flash-Next-FP8-Recreated
```

Qwen3.8-Flash-Next-FP8-Recreated

An independent recreation of Qwen/Qwen3.8-Flash-Next-FP8 from the BF16 release Qwen/Qwen3.8-Flash-Next (rev de4b8e4d): all 152,089 tensors are bitwise identical to the official FP8 checkpoint (rev 236dfdf2). For serving, use the official repo; this one documents the quantization recipe. Not affiliated with or endorsed by Qwen.

Full model card (recipe and verification details) coming soon.

License

Qwen Community License 1.0, Copyright (c) 2026 Qwen (LICENSE). Changes made here (TK-13, 2026-10-24): model-*.safetensors (BF16 release quantized to FP8), config.json (quantization_config added, identical to the official FP8 config), README.md replaced. All other files are unmodified from Qwen/Qwen3.8-Flash-Next.

Downloads last month: 18

Safetensors

Model size

180B params

Tensor type

BF16

F8_E4M3

I64

Model tree for TK-13/Qwen3.8-Flash-Next-FP8-Recreated

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(512)

this model