Instructions to use osunlp/QUEST-30B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use osunlp/QUEST-30B-RL with Transformers:

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

pipe = pipeline("text-generation", model="osunlp/QUEST-30B-RL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("osunlp/QUEST-30B-RL")
model = AutoModelForCausalLM.from_pretrained("osunlp/QUEST-30B-RL")
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 osunlp/QUEST-30B-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "osunlp/QUEST-30B-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osunlp/QUEST-30B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/osunlp/QUEST-30B-RL

SGLang

How to use osunlp/QUEST-30B-RL 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 "osunlp/QUEST-30B-RL" \
    --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": "osunlp/QUEST-30B-RL",
		"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 "osunlp/QUEST-30B-RL" \
        --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": "osunlp/QUEST-30B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use osunlp/QUEST-30B-RL with Docker Model Runner:
```
docker model run hf.co/osunlp/QUEST-30B-RL
```

QUEST-30B-RL

QUEST 30B full model after mid-training → SFT → RL (Qwen3-30B-A3B base, dense). Trained following the same three-stage recipe as the 35B model, evaluated against Tongyi-DR and OpenResearcher at the same scale.

Benchmark results

Benchmark	Metric	Score
BrowseComp	avg@3	37.0
Mind2Web 2	avg@3	28.6
HLE	avg@3	24.6
DeepResearch Bench	avg@3	45.3
BrowseComp-Plus	avg@3	48.2
WideSearch	Item F1 avg@4	54.2
GAIA	avg@3	69.0
LiveResearchBench	avg@3	74.1

Quick start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "osunlp/QUEST-30B-RL"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, device_map="auto", torch_dtype="auto",
)

Apply the model's chat template with tokenizer.apply_chat_template(...) before passing prompts.

License

Released under the Apache License 2.0.

Downloads last month: 48

Safetensors

Model size

31B params

Tensor type

BF16

Collection including osunlp/QUEST-30B-RL

QUEST

Collection

14 items • Updated 3 days ago