LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

MiroThinker 4B SFT V0.2 by miromind-ai

 »  All LLMs  »  miromind-ai  »  MiroThinker 4B SFT V0.2   URL Share it on

  14   
  Agent   Autotrain compatible Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-4b   Conversational   En   Endpoints compatible   Miromind   Open-source   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/miromind-ai/MiroThinker-4B-SFT-v0.2 

MiroThinker 4B SFT V0.2 Benchmarks

LLME Score: 0.26533
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiroThinker 4B SFT V0.2 (miromind-ai/MiroThinker-4B-SFT-v0.2)
🌟 Advertise your project 🚀

MiroThinker 4B SFT V0.2 Parameters and Internals

LLM NameMiroThinker 4B SFT V0.2
Repository 🤗https://huggingface.co/miromind-ai/MiroThinker-4B-SFT-v0.2 
Base Model(s)  Qwen/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM8.1 GB
Updated2025-09-10
Maintainermiromind-ai
Model Typeqwen3
Model Files  4.0 GB: 1-of-3   4.0 GB: 2-of-3   0.1 GB: 3-of-3
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length65536
Model Max Length65536
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to MiroThinker 4B SFT V0.2

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB1028529275
Qwen3 4B Thinking 2507256K / 8.1 GB223556360
Jan V1 4B256K / 8.1 GB12830328
WEBGEN 4B Preview256K / 8.1 GB81067
Qwen3 4B Thinking 2507 FP8256K / 5.2 GB18008231
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB3455428
Qwen3 4B Instruct 2507256K / 8.1 GB384928
...4B Thinking 2507 DAG Reasoning256K / 16.1 GB93284
Jan V1.2509256K / 8.1 GB09
Qwen3 4B Thinking 2507256K / 8.1 GB77284
Note: green Score (e.g. "73.2") means that the model is better than miromind-ai/MiroThinker-4B-SFT-v0.2.

Rank the MiroThinker 4B SFT V0.2 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? 51262 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.
Release v20241124
  Support LLM Explorer