Instructions to use syedazeez/VibeThinker-3B-W4A16-G128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use syedazeez/VibeThinker-3B-W4A16-G128 with Transformers:

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

pipe = pipeline("text-generation", model="syedazeez/VibeThinker-3B-W4A16-G128")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("syedazeez/VibeThinker-3B-W4A16-G128")
model = AutoModelForMultimodalLM.from_pretrained("syedazeez/VibeThinker-3B-W4A16-G128")
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 Settings

vLLM

How to use syedazeez/VibeThinker-3B-W4A16-G128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "syedazeez/VibeThinker-3B-W4A16-G128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "syedazeez/VibeThinker-3B-W4A16-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/syedazeez/VibeThinker-3B-W4A16-G128

SGLang

How to use syedazeez/VibeThinker-3B-W4A16-G128 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 "syedazeez/VibeThinker-3B-W4A16-G128" \
    --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": "syedazeez/VibeThinker-3B-W4A16-G128",
		"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 "syedazeez/VibeThinker-3B-W4A16-G128" \
        --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": "syedazeez/VibeThinker-3B-W4A16-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use syedazeez/VibeThinker-3B-W4A16-G128 with Docker Model Runner:
```
docker model run hf.co/syedazeez/VibeThinker-3B-W4A16-G128
```

VibeThinker-3B-W4A16 (4-bit GPTQ, group size 128)

A 4-bit weight-quantized version of WeiboAI/VibeThinker-3B, produced so the model fits and runs on a 6 GB consumer GPU.

TL;DR — The original BF16 release is 5.8 GB; its weights alone don't fit in 6 GB of VRAM. Quantized to W4A16 (INT4, group size 128) with llmcompressor, the weights shrink to **2.0 GB** and the model serves happily in vLLM on an RTX 3050 6 GB Laptop GPU at ~67 tok/s — with the step-by-step math reasoning intact.

The story

I wanted to run VibeThinker-3B, a small but strong math/STEM reasoning model, on a laptop with an RTX 3050 (6 GB VRAM, 50 W). The problem:

Format	Weights	Fits 6 GB?
BF16 (original)	~5.8 GB	❌ weights alone fill the card; nothing left for KV cache + overhead
W4A16 (this repo)	~2.0 GB	✅ leaves ~2.5 GB for KV cache (≈74k tokens)

So I quantized it locally, then loaded the result back into vLLM and confirmed it produces correct, fully-reasoned answers — all on the 6 GB laptop GPU.

What was done

Method: GPTQ, W4A16 scheme (4-bit symmetric INT weights, FP16 activations), group size 128, lm_head left unquantized.
Tool: llmcompressor 0.12, output in compressed-tensors (pack-quantized) format.
Calibration: 512 samples from HuggingFaceH4/ultrachat_200k @ 2048 tokens.
Hardware used for quantization: RTX 3050 6 GB — the model was loaded on CPU and quantized layer-by-layer (sequential GPU on-loading), keeping peak VRAM ~3.2 GB.

Measured results (RTX 3050 6 GB, vLLM 0.22)

Metric	Value
Weights on GPU	1.99 GiB
KV cache available	2.55 GiB (74,144 tokens)
Max concurrency @ 8192 ctx	9.05×
Throughput	~67 tok/s (eager)
Kernel	Marlin W4A16 + FlashAttention 2

Benchmarks

Both models below are 4-bit, ~2 GB, running on a single RTX 3050 6 GB laptop GPU. Evaluated with lm-evaluation-harness (vLLM backend), 50-sample subset, greedy decode.

Benchmark (metric)	VibeThinker-3B-W4A16	Qwen2.5-3B-Instruct-AWQ
GSM8K (flexible-extract, 5-shot)	84%	70%
ARC-Challenge (acc_norm, 0-shot)	44%	46%

VibeThinker (the math/reasoning specialist) clearly leads on GSM8K math, while the two are comparable on ARC-Challenge general reasoning — the expected "specialist vs generalist" pattern at equal size/footprint.

Notes: 50-sample subset (±~6% stderr), indicative not publishable. ARC is run as 0-shot loglikelihood multiple-choice, which under-represents reasoning models (and is depressed by chat-template wrapping for both), so treat the ARC row as a rough wash. GSM8K is generative and the more meaningful signal here.

Usage (vLLM)

vllm serve syedazeez/VibeThinker-3B-W4A16-G128 \
  --max-model-len 8192 \
  --gpu-memory-utilization 0.92 \
  --dtype float16

from vllm import LLM, SamplingParams

llm = LLM(model="syedazeez/VibeThinker-3B-W4A16-G128",
          max_model_len=8192, gpu_memory_utilization=0.92, dtype="float16")
out = llm.chat(
    [[{"role": "user", "content": "What is the remainder when 7^100 is divided by 13?"}]],
    SamplingParams(temperature=0.6, max_tokens=1500),
)
print(out[0].outputs[0].text)

This is a reasoning model: it emits a <think>...</think> trace before the final answer, so give it a generous max_tokens (≥1500) or the answer may be truncated.

Notes & limitations

Quantization is lossy; on hard benchmarks expect a small quality drop vs the BF16 original. For most math/STEM prompts the reasoning quality is preserved in informal testing.
Inherits the base model's scope: tuned for verifiable tasks (competition math, coding, STEM). Not trained for tool-calling/agents or broad open-domain knowledge.
KV cache fits ~74k tokens at this config, so --max-model-len can be pushed well above 8192 on 6 GB.

License & attribution

This derivative is released under the MIT License, the same license as the original WeiboAI/VibeThinker-3B. All credit for the model itself goes to the original authors. Only the 4-bit quantization was performed here.

@misc{xu2026vibethinker3bexploringfrontierverifiable,
      title={VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models},
      author={Sen Xu and Shixi Liu and Wei Wang and Jixin Min and Yingwei Dai and Zhibin Yin and Yirong Chen and Xin Zhou and Junlin Zhang},
      year={2026},
      eprint={2606.16140},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2606.16140}
}