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

TinyMistral 6x248M Instruct by M4-ai

 »  All LLMs  »  M4-ai  »  TinyMistral 6x248M Instruct   URL Share it on

  646   
  Autotrain compatible Base model:finetune:m4-ai/tiny... Base model:m4-ai/tinymistral-6... Dataset:locutusque/hercules-v1...   En   Endpoints compatible   Instruct   Mixtral   Moe   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/M4-ai/TinyMistral-6x248M-Instruct 

TinyMistral 6x248M Instruct Benchmarks

ARC: 22.44 vs 96.7 (so35)-76.8%
HellaSwag: 27.02 vs 95.3 (gpt4)-71.6%
MMLU: 24.13 vs 88.3 (so35)-72.7%
TruthfulQA: 43.16 vs 59 (gpt4)-26.8%
WinoGrande: 50.59 vs 87.5 (gpt4)-42.2%
LLME Score: 0.19517
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TinyMistral 6x248M Instruct (M4-ai/TinyMistral-6x248M-Instruct)
🌟 Advertise your project 🚀

TinyMistral 6x248M Instruct Parameters and Internals

Model Type 
Language Model (Mixture of Experts)
Use Cases 
Areas:
technical software development, multilingual text generation
Applications:
technical explanations, educational content, policy analysis, problem-solving
Limitations:
Potential biases or harmful content, Not for strict content moderation
Considerations:
Users should be aware of potential biases and exercise caution in sensitive applications.
Additional Notes 
The model is designed for developers and researchers.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
Locutusque/hercules-v1.0
Methodology:
Fine-tuned on the hercules-v1.0 dataset leveraging MoE architecture through LazyMergekit framework.
Model Architecture:
Mixture of Experts (MoE) with several versions of the TinyMistral model.
LLM NameTinyMistral 6x248M Instruct
Repository 🤗https://huggingface.co/M4-ai/TinyMistral-6x248M-Instruct 
Base Model(s)  TinyMistral 6x248M   M4-ai/TinyMistral-6x248M
Model Size1b
Required VRAM4 GB
Updated2025-09-23
MaintainerM4-ai
Model Typemixtral
Instruction-BasedYes
Model Files  4.0 GB
Supported Languagesen
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<|bos|>
Vocabulary Size32005
Torch Data Typefloat32

Best Alternatives to TinyMistral 6x248M Instruct

Best Alternatives
Context / RAM
Downloads
Likes
TinyMistral 6x248M32K / 4 GB64514

Rank the TinyMistral 6x248M Instruct 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? 51534 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