What are the hardware requirements for VibeThinker 3B?

VibeThinker 3B requires approximately 6.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed VibeThinker 3B and how large is it?

VibeThinker 3B is developed by mlx-community, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate VibeThinker 3B?

VibeThinker 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

VibeThinker 3B by mlx-community — VRAM 6.2GB, 128K context

Name: VibeThinker 3B
Author: mlx-community

VibeThinker 3B is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 6.2GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.28.

Base model:finetune:weiboai/vi... Base model:weiboai/vibethinker... Code Conversational En Gpqa Instruct Instruction-following Math Mlx Qwen2 Reasoning Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/VibeThinker-3B

VibeThinker 3B Benchmarks

LLME Score: 0.28209

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

VibeThinker 3B (mlx-community/VibeThinker-3B)

🌟 Advertise your project 🚀

VibeThinker 3B Parameters and Internals

LLM Name	VibeThinker 3B
Repository 🤗	https://huggingface.co/mlx-community/VibeThinker-3B
Base Model(s)	VibeThinker 3B WeiboAI/VibeThinker-3B
Model Size	3b
Required VRAM	6.2 GB
Updated	2026-07-15
Maintainer	mlx-community
Model Type	qwen2
Instruction-Based	Yes
Model Files	5.4 GB: 1-of-2 0.8 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.51.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Quantized Models of the VibeThinker 3B

Model	Likes	Downloads	VRAM
VibeThinker 3B OptiQ 4bit	2	215	2 GB

Best Alternatives to VibeThinker 3B

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 3B	128K / 6.2 GB	63449	747
Saba2 3B	128K / 6.2 GB	6	0
Tessa T1 3B	117K / 6.2 GB	12	5
UIGEN T1.5 3B	117K / 6.2 GB	10	1
Qwen2.5 3B Instruct	32K / 6.2 GB	6840174	521
SmallThinker 3B Preview	32K / 6.8 GB	30529	412
LeeChanRX 3B Instruct	32K / 6.2 GB	570	2
Neuron V1 3B Instruct	32K / 6.2 GB	149	0
Astra Meal Parser	32K / 6.2 GB	50	0
Menda 3B 500	32K / 6.2 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/VibeThinker-3B.

Rank the VibeThinker 3B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 55114 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

VibeThinker 3B by mlx-community