Marketplace · Text & chat
NitrAI/VibeThinker-3B:latest
Call NitrAI/VibeThinker-3B:latest through one OpenAI-compatible API, served by independent machines at prices their owners set. There's no host for it on the grid at this moment (last live 18 Jul 2026) — so the next machine that loads it serves every request for it.
The grid is one machine short.
If your machine already runs open models, it can most likely serve NitrAI/VibeThinker-3B:latest too. Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid.
- Install the connector. One command on the machine that runs your models. It dials out over an encrypted link — no ports to open. The connector
- Load
NitrAI/VibeThinker-3B:latest. It has run here on ollama; any supported engine works. The platform benchmarks it on your hardware first. - Set your price. Developers see your price beside the speed your machine measures.
- Get paid when it's called. Switch it off whenever you like. How hosting works
About NitrAI/VibeThinker-3B:latest.
- Type: Text & chat
- Context window: up to 131,072 tokens
- Runs on: ollama
- First on the grid: 18 Jul 2026
- Hosts serving it now: 0
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
model="NitrAI/VibeThinker-3B:latest",
messages=[{"role": "user", "content": "Hello"}],
)NitrAI/VibeThinker-3B:latest in detail.
VibeThinker-3B is a further exploration of the VibeThinker series at the 3B-parameter scale, focusing on challenging reasoning tasks with clear verification signals, such as mathematics, coding, and STEM. By systematically optimizing the Spectrum-to-Signal Principle (SSP) post-training pipeline introduced in VibeThinker-1.5B, VibeThinker-3B achieves strong performance on AIME, HMMT, IMO-AnswerBenc
- Published by
- WeiboAI
- Parameters
- 3.1B
- Format
- transformers
- Architecture
- qwen2
- Licence
- MIT
- Based on
- Qwen/Qwen2.5-Coder-3B
- Task
- text generation
- Library
- transformers
- Languages
- en
- First published
- 12 Jun 2026
- Last updated
- 30 Jun 2026
- Downloads (30 days)
- 2,840 on Hugging Face
- Likes
- 865
qwen2 text-generation math code reasoning gpqa instruction-following en
The model card
Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.
VibeThinker-3B
🚨 1.This model was not trained on tool-calling or agent-based programming data. We therefore do not recommend using it for tasks that involve function calling, API orchestration, or autonomous coding agents. For programming tasks, we recommend using this model on competitive programming problems (e.g., LeetCode-style).
2.For harder math reasoning, try AMOBench, a problem set harder than the International Mathematical Olympiad (IMO), with included standard answers. Use it to evaluate VibeThinker against other SOTA models. Note: due to extreme difficulty, set max tokens to 60K–100K.
GitHub | ModelScope | Technical Report
Introduction
VibeThinker-3B is a further exploration of the VibeThinker series at the 3B-parameter scale, focusing on challenging reasoning tasks with clear verification signals, such as mathematics, coding, and STEM. By systematically optimizing the Spectrum-to-Signal Principle (SSP) post-training pipeline introduced in VibeThinker-1.5B, VibeThinker-3B achieves strong performance on AIME, HMMT, IMO-AnswerBench, LiveCodeBench, and recent LeetCode contests, reaching the performance range of top-tier frontier reasoning models, including Qwen3.6 Plus, Gemini 3 Pro, GLM-5, and Kimi K2.5, on verifiable reasoning benchmarks.
Motivated by these observations, we propose the Parametric Compression-Coverage Hypothesis: different capabilities depend on model parameters in fundamentally different ways. Verifiable reasoning is closer to a highly compressible, parameter-dense capability, centered on multi-step reasoning, constraint satisfaction, self-correction, and answer verification. When the task space is sufficiently structured and feedback signals are sufficiently reliable, compact models may also carry near-frontier reasoning capabilities. In contrast, open-domain knowledge, general-purpose dialogue, and long-tail scenario understanding rely more heavily on large-scale parameters to broadly cover facts, concepts, and world knowledge.
From VibeThinker-1.5B to VibeThinker-3B, our goal is not to build a small model that replaces large-scale models, but to examine the real boundaries of small models along specific capability dimensions. With VibeThinker-3B, we aim to show that small models should not be viewed merely as a compromise for reducing deployment costs. For capability domains with clear feedback and verification mechanisms, SLMs emerge as a promising research trajectory toward frontier-level performance that is fundamentally complementary to the traditional parameter scaling paradigm.
Key Performance Data
📏 In terms of reasoning accuracy relative to model scale, VibeThinker-3B reaches 76.4 on IMO-AnswerBench, a highly challenging benchmark with 400 IMO-level problems, with only 3B parameters, and improves to 80.6 with Claim-Level Reliability Assessment (CLR), a test-time scaling strategy for answer-verifiable reasoning tasks. This demonstrates that a model within a strictly small-model regime can reach the performance range of substantially larger models, such as DeepSeek V3.2 (78.3, 671B), GLM-5 (82.5, 744B), and Kimi K2.5 (81.8, 1T).
💡 VibeThinker-3B achieves strong results across mathematics, coding, knowledge, and instruction-following benchmarks.
🔁 VibeThinker-3B achieves competitive results against first-tier reasoning models and reaches the performance range of top-tier systems on several verifiable reasoning benchmarks.
🏆 To further test the model's out-of-distribution performance, we evaluate VibeThinker-3B on recent unseen LeetCode weekly and biweekly contests (Python) from Apr. 25 to May 31, 2026. VibeThinker-3B passes 123/128 first-attempt submissions, corresponding to a 96.1% acceptance rate.
Read the rest of the model card
Training Pipeline
VibeThinker-3B follows the Spectrum-to-Signal Principle (SSP) introduced in VibeThinker-1.5B. The SFT stage constructs a broad spectrum of valid reasoning trajectories, while the RL stage amplifies correct reasoning signals using verifiable rewards.
The training pipeline contains the following stages:
- Curriculum-based two-stage SFT
- Stage 1 focuses on broad capability coverage across math, code, STEM reasoning, general dialogue, and instruction following.
- Stage 2 shifts toward harder and longer-horizon reasoning samples.
- Diversity-Exploring Distillation is used to preserve multiple valid solution paths.
- Multi-domain Reasoning RL
- VibeThinker-3B reuses MaxEnt-Guided Policy Optimization (MGPO).
- RL is applied sequentially to math, code, and STEM reasoning tasks.
- Training uses a single 64K long-context window to preserve complete long-horizon reasoning trajectories.
- Offline Self-Distillation
- High-quality trajectories from Math, Code, and STEM RL checkpoints are filtered and distilled back into a unified student model.
- A learning-potential score is used to prioritize traces that are correct but not yet well modeled by the student.
- Instruct RL
- The final stage improves controllability on user-facing prompts.
- Rule-based validators and rubric-based reward models are used for format-sensitive and open-ended instruction data.
Usage Guidelines
We recommend using VibeThinker-3B for competitive-style math, coding, STEM reasoning, and other tasks where the target answer can be verified. For broad open-domain knowledge tasks, larger general-purpose models may still be more suitable.
For benchmark-style evaluation, the technical report uses vLLM with:
temperature=1.0top_p=0.95top_k=-1
Quick Start
Required: transformers>=4.54.0
Recommended for better inference performance: vLLM==0.10.1 or SGLang>=0.4.9.post6
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
class VibeThinker:
def __init__(self, model_path):
self.model_path = model_path
self.model = AutoModelForCausalLM.from_pretrained(
self.model_path,
low_cpu_mem_usage=True,
torch_dtype="bfloat16",
device_map="auto",
)
self.tokenizer = AutoTokenizer.from_pretrained(
self.model_path,
trust_remote_code=True,
)
def infer_text(self, prompt):
messages = [{"role": "user", "content": prompt}]
text = self.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
model_inputs = self.tokenizer([text], return_tensors="pt").to(self.model.device)
generation_config = dict(
max_new_tokens=102400,
do_sample=True,
temperature=1.0,
top_p=0.95,
top_k=None,
)
generated_ids = self.model.generate(
**model_inputs,
generation_config=GenerationConfig(**generation_config),
)
generated_ids = [
output_ids[len(input_ids):]
for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
return self.tokenizer.batch_decode(
generated_ids,
skip_special_tokens=True,
)[0]
if __name__ == "__main__":
model = VibeThinker("WeiboAI/VibeThinker-3B")
prompt = "Your Prompt"
print(model.infer_text(prompt))
License
The model repository is licensed under the MIT License.
Citations & References
If you use VibeThinker-3B in your research or product, please cite:
@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},
}Sources: WeiboAI/VibeThinker-3B on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.
Live now instead.
Similar text & chat models with hosts serving them right now.
- qwen2.5:0.5b — from £0.009 per 1M output tokens · 5 hosts
- functiongemma:latest — from £0.015 per 1M output tokens · 4 hosts
- glm-ocr:latest — from £0.06 per 1M output tokens · 3 hosts
- granite4.2:3b — from £0.06 per 1M output tokens · 3 hosts
- lfm3:latest — from £0.043 per 1M output tokens · 3 hosts
- llama-guard3:1b — from £0.018 per 1M output tokens · 3 hosts
Questions about NitrAI/VibeThinker-3B:latest.
Can I use NitrAI/VibeThinker-3B:latest through an API?
Yes. Inpherio serves NitrAI/VibeThinker-3B:latest through one OpenAI-compatible API whenever a host on the grid is running it — the code on this page works unchanged. With no host right now, a call returns a "not available on any node" error and is never charged, and similar models are live on the marketplace.
How do I host NitrAI/VibeThinker-3B:latest and get paid?
Install the Inpherio connector on the machine that runs your models, load NitrAI/VibeThinker-3B:latest in a supported engine, and set a price. The platform benchmarks it on your hardware, then requests for it reach your machine. Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid.
Why is NitrAI/VibeThinker-3B:latest not being served right now?
Hosts on Inpherio are independent machines that come and go. It was last live on 18 Jul 2026. When a host loads it again, this page shows live prices and measured speeds.