Instructions to use cerebras/Qwen3-Coder-REAP-25B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cerebras/Qwen3-Coder-REAP-25B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="cerebras/Qwen3-Coder-REAP-25B-A3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cerebras/Qwen3-Coder-REAP-25B-A3B")
model = AutoModelForCausalLM.from_pretrained("cerebras/Qwen3-Coder-REAP-25B-A3B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cerebras/Qwen3-Coder-REAP-25B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cerebras/Qwen3-Coder-REAP-25B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cerebras/Qwen3-Coder-REAP-25B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cerebras/Qwen3-Coder-REAP-25B-A3B

SGLang

How to use cerebras/Qwen3-Coder-REAP-25B-A3B 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 "cerebras/Qwen3-Coder-REAP-25B-A3B" \
    --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": "cerebras/Qwen3-Coder-REAP-25B-A3B",
		"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 "cerebras/Qwen3-Coder-REAP-25B-A3B" \
        --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": "cerebras/Qwen3-Coder-REAP-25B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cerebras/Qwen3-Coder-REAP-25B-A3B with Docker Model Runner:
```
docker model run hf.co/cerebras/Qwen3-Coder-REAP-25B-A3B
```

NVFP4?

by ktsaou - opened Dec 25, 2025

Discussion

ktsaou

Dec 25, 2025

@Firworks it would be great if you could convert this model to nvfp4!

Firworks

Dec 26, 2025

Here it is if you'd like to give it a try! I'm having issues running it in VLLM on an RTX Pro 6000 Blackwell instance. There appear to be some outstanding vllm issues with patches that aren't released yet that may fix this. I added a note on the model card. It should work as is with Transformers though.

https://huggingface.co/Firworks/Qwen3-Coder-REAP-25B-A3B-nvfp4

ktsaou

Dec 26, 2025

Wow! You rock!

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