Instructions to use Qwen/Qwen3.8-Flash-Next with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3.8-Flash-Next with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Qwen/Qwen3.8-Flash-Next") 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-Flash-Next") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.8-Flash-Next", 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Qwen/Qwen3.8-Flash-Next with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen3.8-Flash-Next" # 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-Flash-Next", "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-Flash-Next
- SGLang
How to use Qwen/Qwen3.8-Flash-Next 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-Flash-Next" \ --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-Flash-Next", "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-Flash-Next" \ --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-Flash-Next", "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-Flash-Next with Docker Model Runner:
docker model run hf.co/Qwen/Qwen3.8-Flash-Next
Qwen3.8 35B-A5B PLS
Can I please have the 35B-A5B version?
SPEED I NEED THIS
FRs we need that
Can I please have the 35B-A5B version?
a3b will be better tho.
Can I please have the 35B-A5B version?
a3b will be better tho.
agree
Can We?
Is there any version with 35 total BI parameters available?
I need to be able to run it in a 3090.
The 3.8-27B is very good, but slow... indeed if 35B-A3B variant available will be much more preferable
https://huggingface.co/bartowski/occamy-ai_occamy-1.0-GGUF
I think this is the best 35B-A3B llm out to date, very pleased with it.
Hopefully it will have a Qwen 3.8 version if it ever lands
This model is definitely better, just give it a try: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
This model is definitely better, just give it a try: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
meh,i alr downloaded it but you send cyber tiel(ablirated one) but why
This model is definitely better, just give it a try: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
meh,i alr downloaded it but you send cyber tiel(ablirated one) but why
What do you mean? I provided that link to someone else, if you're asking why specifically the abliterated version, it outperforms the standard Tiel Coder in my tests—and even according to the developer.
https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/discussions/3
https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/resolve/main/assets/cybertiel_bench_swe.gif
This model is definitely better, just give it a try: https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
meh,i alr downloaded it but you send cyber tiel(ablirated one) but why
What do you mean? I provided that link to someone else, if you're asking why specifically the abliterated version, it outperforms the standard Tiel Coder in my tests—and even according to the developer.
https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/discussions/3
https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP/resolve/main/assets/cybertiel_bench_swe.gif
For some reason, Hugging Face sent me a notification too; I didn't look closely enough and thought it was a reply to me—I apologize.