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

Medtulu 4x7B by Technoculture

 »  All LLMs  »  Technoculture  »  Medtulu 4x7B   URL Share it on

  1648   
  Allenai/tulu-2-dpo-7b   Autotrain compatible Chaoyi-wu/pmc llama 7b 10 epoc...   Endpoints compatible   Epfl-llm/meditron-7b   Medalpaca/medalpaca-7b   Merge   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Technoculture/Medtulu-4x7B 

Medtulu 4x7B Benchmarks

ARC: 28.75 vs 96.7 (so35)-70.3%
HellaSwag: 25.74 vs 95.3 (gpt4)-73%
MMLU: 24.41 vs 88.3 (so35)-72.4%
TruthfulQA: 47.91 vs 59 (gpt4)-18.8%
WinoGrande: 50.43 vs 87.5 (gpt4)-42.4%
LLME Score: 0.19688
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Medtulu 4x7B (Technoculture/Medtulu-4x7B)
🌟 Advertise your project 🚀

Medtulu 4x7B Parameters and Internals

Model Type 
text-generation
Additional Notes 
Mediquad-tulu-20B is an MoE model using components like epfl-llm/meditron-7b, medalpaca/medalpaca-7b, chaoyi-wu/PMC_LLAMA_7B_10_epoch, and allenai/tulu-2-dpo-7b.
LLM NameMedtulu 4x7B
Repository 🤗https://huggingface.co/Technoculture/Medtulu-4x7B 
Model Size19.7b
Required VRAM39.4 GB
Updated2025-09-21
MaintainerTechnoculture
Model Typemixtral
Model Files  10.0 GB: 1-of-4   9.9 GB: 2-of-4   9.9 GB: 3-of-4   9.6 GB: 4-of-4
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Medtulu 4x7B

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 4x7B Experts Base16K / 39.5 GB50
Magician MoE 4x7B16K / 78.8 GB16501
Mediquad 4x7b8K / 39.4 GB16690
Medorca 4x7b4K / 39.4 GB16680
GOAT Adapt MoE 4x7B2K / 39.4 GB53
Note: green Score (e.g. "73.2") means that the model is better than Technoculture/Medtulu-4x7B.

Rank the Medtulu 4x7B 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? 51507 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