Instructions to use Qwen/Qwen3.8-2.4T-A95B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3.8-2.4T-A95B with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3.8-2.4T-A95B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3.8-2.4T-A95B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.8-2.4T-A95B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3.8-2.4T-A95B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3.8-2.4T-A95B"
# 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/Qwen3.8-2.4T-A95B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3.8-2.4T-A95B

SGLang

How to use Qwen/Qwen3.8-2.4T-A95B 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/Qwen3.8-2.4T-A95B" \
    --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/Qwen3.8-2.4T-A95B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Qwen3.8-2.4T-A95B" \
        --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/Qwen3.8-2.4T-A95B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3.8-2.4T-A95B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3.8-2.4T-A95B
```

Looking forward to a ternary GGUF for this version

#22

by kreels - opened Aug 13

Discussion

kreels

Aug 13

I could maybe run it then on my funny old hardware.

bleaki

Aug 13

Even a 1bit / ternary of a 2.4T model would need decent hardware,
The 27b model they used that lots of people tried and were impressed with was like 3gb,
2.4T ÷ 27b = 88888.9,
A full sized 27b model fits on a single 5090 no problem, Im not sure you'd fit the ternary of a 2.4T model on a 5090

maglun

Aug 13

•

edited Aug 13

Ternary averages out to ~1.6 - 1.7 bit per weight, so we are looking at ~500 GB at least depending on how much you keep some tensors at higher bpw

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