Instructions to use tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ")
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("tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ")
model = AutoModelForMultimodalLM.from_pretrained("tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ", 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 tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ",
		"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/tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ

SGLang

How to use tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ 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 "tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ" \
    --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": "tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ",
		"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 "tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ" \
        --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": "tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ",
		"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 tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ with Docker Model Runner:
```
docker model run hf.co/tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ
```

tcclaviger commited on 16 days ago

Commit

d64bb4c

verified ·

1 Parent(s): 99f1ca9

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -21,9 +21,9 @@ tags:
 <li>Experts: MXFP4 (activation-aware) — 64.2 GB</li>
 <li>N-Gram: int6 — 41.6 GB</li>
 <li>Attention: FP8 — 2.7 GB</li>
-<li>PPL: 4.552 (old mxpf4 version 4.603)</li>
-<li>KLD: .0549 vs static .0638</li>
-<li>Top1: 95.17% vs static 93.26%</li>
 </ul>
 <p>Calibrated FP8 KV-cache scales are included.</p>
 <p>AMD RAM offload has been enabled.</p>

 <li>Experts: MXFP4 (activation-aware) — 64.2 GB</li>
 <li>N-Gram: int6 — 41.6 GB</li>
 <li>Attention: FP8 — 2.7 GB</li>
+<li>PPL: 4.552 vs old mxpf4 version 4.603</li>
+<li>KLD: .0549 vs old mxpf4 version .0638</li>
+<li>Top1: 95.17% vs old mxpf4 version 93.26%</li>
 </ul>
 <p>Calibrated FP8 KV-cache scales are included.</p>
 <p>AMD RAM offload has been enabled.</p>