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

KitchenSink 103B by MarsupialAI

 »  All LLMs  »  MarsupialAI  »  KitchenSink 103B   URL Share it on

  13   

KitchenSink 103B is an open-source language model by MarsupialAI. Features: 103b LLM, VRAM: 178.6GB, Context: 4K, License: llama2, LLM Explorer Score: 0.11.

  Chat   En   Endpoints compatible   Erp   Llama   Region:us   Rp   Safetensors   Sharded   Storywriting   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MarsupialAI/KitchenSink_103b 

KitchenSink 103b Benchmarks

LLME Score: 0.11155
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
KitchenSink 103B (MarsupialAI/KitchenSink_103b)
🌟 Advertise your project 🚀

KitchenSink 103B Parameters and Internals

LLM NameKitchenSink 103b
Repository 🤗https://huggingface.co/MarsupialAI/KitchenSink_103b 
Model Size103b
Required VRAM178.6 GB
Updated2026-05-17
MaintainerMarsupialAI
Model Typellama
Model Files  4.0 GB: 1-of-55   3.9 GB: 2-of-55   3.9 GB: 3-of-55   3.6 GB: 4-of-55   3.9 GB: 5-of-55   3.6 GB: 6-of-55   3.9 GB: 7-of-55   3.9 GB: 8-of-55   3.7 GB: 9-of-55   3.9 GB: 10-of-55   3.9 GB: 11-of-55   3.7 GB: 12-of-55   3.6 GB: 13-of-55   3.9 GB: 14-of-55   3.7 GB: 15-of-55   3.6 GB: 16-of-55   3.9 GB: 17-of-55   3.9 GB: 18-of-55   3.9 GB: 19-of-55   3.6 GB: 20-of-55   3.9 GB: 21-of-55   3.7 GB: 22-of-55   3.6 GB: 23-of-55   3.8 GB: 24-of-55   3.9 GB: 25-of-55   3.6 GB: 26-of-55   3.9 GB: 27-of-55   3.9 GB: 28-of-55   3.7 GB: 29-of-55   3.9 GB: 30-of-55   3.7 GB: 31-of-55   3.6 GB: 32-of-55   3.9 GB: 33-of-55   3.9 GB: 34-of-55   3.9 GB: 35-of-55   3.9 GB: 36-of-55   3.7 GB: 37-of-55   3.9 GB: 38-of-55   3.5 GB: 39-of-55   3.9 GB: 40-of-55   3.9 GB: 41-of-55   3.9 GB: 42-of-55   3.7 GB: 43-of-55   3.9 GB: 44-of-55   3.6 GB: 45-of-55   3.9 GB: 46-of-55   3.9 GB: 47-of-55
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to KitchenSink 103B

Best Alternatives
Context / RAM
Downloads
Likes
Dark Miqu 103B31K / 206.4 GB302
BigWeave V15 103B31K / 206.6 GB892
Midnight Miqu 103B V1.531K / 206.4 GB8626
Midnight Miqu 103B V1.031K / 206.4 GB8516
Midnight Rose 103B V2.0.34K / 206.6 GB8911
OmegaDolphin 103B V0.14K / 175.6 GB71
Midnight Rose 103B V1.04K / 206.6 GB43
Aurora Nights 103B V1.04K / 206.6 GB1114
Rogue Rose 103B V0.24K / 206.5 GB933
Lila 103B L24K / 206.2 GB00
Note: green Score (e.g. "73.2") means that the model is better than MarsupialAI/KitchenSink_103b.

Rank the KitchenSink 103B 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? 53972 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