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

Marco Mini Base by AIDC-AI

 »  All LLMs  »  AIDC-AI  »  Marco Mini Base   URL Share it on

  372   

Marco Mini Base is an open-source language model by AIDC-AI. Features: 100b LLM, VRAM: 34.8GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.35.

  Ar   Az   Bn   Conversational   Cs Dataset:allenai/dolma3 dolmino... Dataset:allenai/dolmino-mix-11... Dataset:huggingfacefw/fineweb-...   Dataset:huggingfacetb/finemath   Dataset:llm360/megamath Dataset:nvidia/nemotron-cc-mat...   Dataset:nvidia/nemotron-cc-v2 Dataset:nvidia/nemotron-cc-v2.... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/nemotron-pretra... Dataset:nvidia/openmathinstruc... Dataset:open-thoughts/openthou... Dataset:opencsg/fineweb-edu-ch...   De   El   En   Endpoints compatible   Es   Fr   He   Hu   Id   It   Ja   Kk   Ko   Mixture-of-experts   Moe   Ms   Multilingual   Ne   Nl   Pl   Pt   Qwen3 moe   Region:us   Ro   Ru   Safetensors   Sharded   Tensorflow   Th   Tr   Uk   Upcycling   Ur   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/AIDC-AI/Marco-Mini-Base 

Marco Mini Base Benchmarks

LLME Score: 0.3547
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Marco Mini Base (AIDC-AI/Marco-Mini-Base)
🌟 Advertise your project 🚀

Marco Mini Base Parameters and Internals

LLM NameMarco Mini Base
Repository 🤗https://huggingface.co/AIDC-AI/Marco-Mini-Base 
Model Size100b
Required VRAM34.8 GB
Updated2026-04-04
MaintainerAIDC-AI
Model Typeqwen3_moe
Model Files  2.0 GB: 1-of-18   2.0 GB: 2-of-18   2.0 GB: 3-of-18   2.0 GB: 4-of-18   2.0 GB: 5-of-18   2.0 GB: 6-of-18   2.0 GB: 7-of-18   2.0 GB: 8-of-18   2.0 GB: 9-of-18   2.0 GB: 10-of-18   2.0 GB: 11-of-18   2.0 GB: 12-of-18   2.0 GB: 13-of-18   2.0 GB: 14-of-18   2.0 GB: 15-of-18   2.0 GB: 16-of-18   2.0 GB: 17-of-18   0.8 GB: 18-of-18
Supported Languagesen zh ar de es fr ko ja pt tr id it nl pl ru vi th he uk ms bn cs ur kk el ro hu ne az
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Rank the Marco Mini Base 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? 52554 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