VibeThinker 3B SFT Fable5 Glint by ermiaazarkhalili

 »  All LLMs  »  ermiaazarkhalili  »  VibeThinker 3B SFT Fable5 Glint   URL Share it on

VibeThinker 3B SFT Fable5 Glint is an open-source language model by ermiaazarkhalili. Features: 3b LLM, VRAM: 6.2GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.28.

Base model:finetune:weiboai/vi... Base model:weiboai/vibethinker...   Conversational   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

VibeThinker 3B SFT Fable5 Glint Benchmarks

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

VibeThinker 3B SFT Fable5 Glint Parameters and Internals

LLM NameVibeThinker 3B SFT Fable5 Glint
Repository 🤗https://huggingface.co/ermiaazarkhalili/VibeThinker-3B-SFT-Fable5-Glint 
Base Model(s)  VibeThinker 3B   WeiboAI/VibeThinker-3B
Model Size3b
Required VRAM6.2 GB
Updated2026-06-29
Maintainerermiaazarkhalili
Model Typeqwen2
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to VibeThinker 3B SFT Fable5 Glint

Best Alternatives
Context / RAM
Downloads
Likes
VibeThinker 3B128K / 6.2 GB63449747
VibeThinker 3B128K / 6.2 GB1970
Saba1.5 Pro 3B128K / 5.8 GB101
...b Sft Stage1.2 Ss1 Expert Math128K / 15.1 GB70
...b Sft Stage1.2 Ss1 Expert News128K / 15.1 GB660
...2 Ss1 Expert Fictional Lyrical128K / 15.1 GB50
... Formattedtext Math Wiki Merge128K / 15.1 GB50
...tage1.1 Ss1 With Math.no Issue128K / 15.1 GB70
...ware Howto Formattedtext Merge128K / 15.1 GB60
...1 No Redteam Skg Poem.no Issue128K / 15.1 GB70
Note: green Score (e.g. "73.2") means that the model is better than ermiaazarkhalili/VibeThinker-3B-SFT-Fable5-Glint.

Rank the VibeThinker 3B SFT Fable5 Glint 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? 54653 in total.

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