Instructions to use osunlp/QUEST-35B-MT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use osunlp/QUEST-35B-MT with Transformers:

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

pipe = pipeline("text-generation", model="osunlp/QUEST-35B-MT")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("osunlp/QUEST-35B-MT")
model = AutoModelForImageTextToText.from_pretrained("osunlp/QUEST-35B-MT")
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

vLLM

How to use osunlp/QUEST-35B-MT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "osunlp/QUEST-35B-MT"
# 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-35B-MT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/osunlp/QUEST-35B-MT

SGLang

How to use osunlp/QUEST-35B-MT 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-35B-MT" \
    --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-35B-MT",
		"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-35B-MT" \
        --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-35B-MT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use osunlp/QUEST-35B-MT with Docker Model Runner:
```
docker model run hf.co/osunlp/QUEST-35B-MT
```

hsaest commited on 13 days ago

Commit

aedaa8a

verified ·

1 Parent(s): 6212079

README: add benchmark result table from project page

Browse files

Files changed (1) hide show

README.md +17 -6

README.md CHANGED Viewed

@@ -9,7 +9,20 @@ tags:
 # QUEST-35B-MT
-**Qwen3.5 MoE**-style **35B-class** checkpoint after **mid-training** (`Qwen3_5MoeForConditionalGeneration`). Expect higher VRAM / expert routing behavior than dense 30B models.
 ## Quick start
@@ -19,14 +32,12 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 model_id = "osunlp/QUEST-35B-MT"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    device_map="auto",
-    torch_dtype="auto",
 )
 ```
-Use the chat template and `tokenizer.apply_chat_template(...)` when available. VRAM and dtype requirements depend on model size and MoE vs dense architecture; see `config.json` (`model_type`, `architectures`).
 ## License
-This model is released under the **Apache License 2.0** (`apache-2.0`).

 # QUEST-35B-MT
+QUEST **35B-class MoE** checkpoint after **mid-training + SFT** (Qwen3.5-35B-A3B base). This is the +MT stage in the training progression (Vanilla → SFT → **MT+SFT** → RL).
+## Benchmark results
+| Benchmark | Metric | Score |
+| --- | --- | ---: |
+| BrowseComp | avg@3 | 45.5 |
+| Mind2Web 2 | avg@3 | 29.9 |
+| HLE | avg@3 | 39.74 |
+| DeepResearch Bench | avg@3 | 39.72 |
+| BrowseComp-Plus | avg@3 | 58.6 |
+| WideSearch | Item F1 avg@4 | 62.5 |
+| GAIA | avg@3 | 83.17 |
+| LiveResearchBench | avg@3 | 65.47 |
 ## Quick start
 model_id = "osunlp/QUEST-35B-MT"
 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**.