Instructions to use WeiboAI/VibeThinker-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WeiboAI/VibeThinker-3B with Transformers:

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

pipe = pipeline("text-generation", model="WeiboAI/VibeThinker-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WeiboAI/VibeThinker-3B")
model = AutoModelForCausalLM.from_pretrained("WeiboAI/VibeThinker-3B")
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
Local Apps Settings

vLLM

How to use WeiboAI/VibeThinker-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WeiboAI/VibeThinker-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WeiboAI/VibeThinker-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WeiboAI/VibeThinker-3B

SGLang

How to use WeiboAI/VibeThinker-3B 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 "WeiboAI/VibeThinker-3B" \
    --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": "WeiboAI/VibeThinker-3B",
		"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 "WeiboAI/VibeThinker-3B" \
        --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": "WeiboAI/VibeThinker-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WeiboAI/VibeThinker-3B with Docker Model Runner:
```
docker model run hf.co/WeiboAI/VibeThinker-3B
```

Add evaluation results from model card benchmark tables

#21

by SaylorTwift HF Staff - opened 7 days ago

base: refs/heads/main

←

from: refs/pr/21

Discussion Files changed

+34

-0

Files changed (1) hide show

.eval_results/vibethinker-3b.yaml +34 -0

.eval_results/vibethinker-3b.yaml ADDED Viewed

	@@ -0,0 +1,34 @@

+# Evaluation results for WeiboAI/VibeThinker-3B
+# Extracted from the model card benchmark tables (pictures/VibeThiinker-3B.png, pictures/VibeThinker-3B+CLR.png)
+# https://huggingface.co/WeiboAI/VibeThinker-3B
+# Paper: https://huggingface.co/papers/2606.16140
+# ---------------------------------------------------------------------------
+# Mathematics
+# ---------------------------------------------------------------------------
+# AIME 2026 - 94.3
+- dataset:
+    id: MathArena/aime_2026
+    task_id: MathArena/aime_2026
+  value: 94.3
+  date: "2026-06-19"
+  source:
+    url: https://huggingface.co/WeiboAI/VibeThinker-3B
+    name: VibeThinker-3B model card evaluation table
+  notes: "Evaluated with vLLM, temperature=1.0, top_p=0.95, top_k=-1."
+# ---------------------------------------------------------------------------
+# Knowledge / Reasoning
+# ---------------------------------------------------------------------------
+# GPQA Diamond - 70.2
+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 70.2
+  date: "2026-06-19"
+  source:
+    url: https://huggingface.co/WeiboAI/VibeThinker-3B
+    name: VibeThinker-3B model card evaluation table
+  notes: "Evaluated with vLLM, temperature=1.0, top_p=0.95, top_k=-1."