VibeThinker 1.5B by WeiboAI

 ยป  All LLMs  ยป  WeiboAI  ยป  VibeThinker 1.5B   URL Share it on

VibeThinker 1.5B is an open-source language model by WeiboAI. Features: 1.5b LLM, VRAM: 3.5GB, Context: 128K, License: mit, LLM Explorer Score: 0.36.

  Arxiv:2511.06221 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-math-1...   Code   Conversational   Deploy:azure   En   Endpoints compatible   Gpqa   Math   Qwen2   Region:us   Safetensors

VibeThinker 1.5B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
VibeThinker 1.5B (WeiboAI/VibeThinker-1.5B)
๐ŸŒŸ Advertise your project ๐Ÿš€

VibeThinker 1.5B Parameters and Internals

LLM NameVibeThinker 1.5B
Repository ๐Ÿค—https://huggingface.co/WeiboAI/VibeThinker-1.5B 
Base Model(s)  Qwen/Qwen2.5-Math-1.5B   Qwen/Qwen2.5-Math-1.5B
Model Size1.5b
Required VRAM3.5 GB
Updated2026-03-27
MaintainerWeiboAI
Model Typeqwen2
Model Files  3.5 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.56.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Quantized Models of the VibeThinker 1.5B

Model
Likes
Downloads
VRAM
VibeThinker 1.5B Mlx 4bit241670 GB

Best Alternatives to VibeThinker 1.5B

Best Alternatives
Context / RAM
Downloads
Likes
ReaderLM V2500K / 3.1 GB2591766
Reader Lm 1.5B250K / 3.1 GB1411607
DeepSeek R1 Distill Qwen 1.5B128K / 3.5 GB12145231427
Qwen2.5 1.5B128K / 3.1 GB888741150
AceInstruct 1.5B128K / 3.5 GB7688020
DeepScaleR 1.5B Preview128K / 7.1 GB11774573
...n Research Reasoning Qwen 1.5B128K / 7.1 GB5716221
Qwen2 1.5B128K / 3.1 GB8373497
Stella En 1.5B V5128K / 6.2 GB581890211
OpenReasoning Nemotron 1.5B128K / 3.1 GB518847
Note: green Score (e.g. "73.2") means that the model is better than WeiboAI/VibeThinker-1.5B.

Rank the VibeThinker 1.5B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52052 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260327b