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

Mixsmol 4x400M V0.1 Epoch1 by vilm

 »  All LLMs  »  vilm  »  Mixsmol 4x400M V0.1 Epoch1   URL Share it on

  79   

Mixsmol 4x400M V0.1 Epoch1 is an open-source language model by vilm. Features: 1.8b LLM, VRAM: 3.5GB, Context: 4K, License: apache-2.0, MoE, HF Score: 28.5, LLM Explorer Score: 0.17, Arc: 22.9, HellaSwag: 30.6, MMLU: 25.3, TruthfulQA: 39, WinoGrande: 52.8, GSM8K: 0.2.

  Endpoints compatible   Mixtral   Moe   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/vilm/Mixsmol-4x400M-v0.1-epoch1 

Mixsmol 4x400M V0.1 Epoch1 Benchmarks

ARC: 22.87 vs 96.7 (so35)-76.3%
HellaSwag: 30.57 vs 95.3 (gpt4)-67.9%
MMLU: 25.28 vs 88.3 (so35)-71.4%
TruthfulQA: 39.03 vs 59 (gpt4)-33.8%
WinoGrande: 52.8 vs 87.5 (gpt4)-39.7%
GSM8K: 0.15 vs 96.4 (so35)-99.8%
LLME Score: 0.16709
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixsmol 4x400M V0.1 Epoch1 (vilm/Mixsmol-4x400M-v0.1-epoch1)
🌟 Advertise your project 🚀

Mixsmol 4x400M V0.1 Epoch1 Parameters and Internals

Additional Notes 
This is an experimental model focusing on data mixing skills with limited data training to test reasoning capabilities and crosslingual understanding.
Supported Languages 
English (95%), Vietnamese (5%)
Training Details 
Data Sources:
Synthetic Textbooks, RefinedWeb, RedPajama-v2, MathPile, ThePile: MiniPile Subset, GoodWiki, The Stack Smol XL, The Vault: train_small split, Instruction Pretraining
Data Volume:
50B tokens
LLM NameMixsmol 4x400M V0.1 Epoch1
Repository 🤗https://huggingface.co/vilm/Mixsmol-4x400M-v0.1-epoch1 
Model Size1.8b
Required VRAM3.5 GB
Updated2026-04-06
Maintainervilm
Model Typemixtral
Model Files  3.5 GB   0.0 GB
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size38365
Torch Data Typebfloat16

Best Alternatives to Mixsmol 4x400M V0.1 Epoch1

Best Alternatives
Context / RAM
Downloads
Likes
Mixsmol 4x400M V0.1 Epoch24K / 3.5 GB25
Mixsmol 4x400M V0.1 Epoch34K / 3.5 GB55
Mixtral 4x400M4K / 7.1 GB122
Tiny Llama 1.8B2K / 3.7 GB00

Rank the Mixsmol 4x400M V0.1 Epoch1 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? 52721 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