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

Umbra V3 MoE 4x11b by SteelStorage

 »  All LLMs  »  SteelStorage  »  Umbra V3 MoE 4x11b   URL Share it on

  5   
  Autotrain compatible Base model:beberik/nyxene-v3-1... Base model:decapoda-research/a...   Base model:himitsui/kaiju-11b Base model:merge:beberik/nyxen... Base model:merge:decapoda-rese... Base model:merge:himitsui/kaij... Base model:merge:sao10k/fimbul... Base model:sao10k/fimbulvetr-1...   Beberik/nyxene-v3-11b   Conversational Decapoda-research/antares-11b-...   Endpoints compatible   Frankenmoe   Himitsui/kaiju-11b   Merge   Mergekit   Mixtral   Model-index   Moe   Region:us   Safetensors   Sao10k/fimbulvetr-11b-v2   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/SteelStorage/Umbra-v3-MoE-4x11b 

Umbra V3 MoE 4x11b Benchmarks

LLME Score: 0.14138
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Umbra V3 MoE 4x11b (SteelStorage/Umbra-v3-MoE-4x11b)
🌟 Advertise your project 🚀

Umbra V3 MoE 4x11b Parameters and Internals

Model Type 
moe, frankenmoe, merge, mergekit
Additional Notes 
Umbra v3 aims to be a versatile tool with storytelling prowess. Noteworthy performance across several challenges.
Release Notes 
Version:
v3
Notes:
Upgraded models, improved storytelling and RP/ERP capabilities. Enhanced positive prompt handling.
LLM NameUmbra V3 MoE 4x11b
Repository 🤗https://huggingface.co/SteelStorage/Umbra-v3-MoE-4x11b 
Base Model(s)  Kaiju 11B   Fimbulvetr 11B V2   Antares 11B V2   Nyxene V3 11B   Himitsui/Kaiju-11B   Sao10K/Fimbulvetr-11B-v2   decapoda-research/Antares-11b-v2   beberik/Nyxene-v3-11B
Model Size36.1b
Required VRAM72.3 GB
Updated2025-09-23
MaintainerSteelStorage
Model Typemixtral
Model Files  9.9 GB: 1-of-8   10.0 GB: 2-of-8   10.0 GB: 3-of-8   10.0 GB: 4-of-8   10.0 GB: 5-of-8   10.0 GB: 6-of-8   10.0 GB: 7-of-8   2.4 GB: 8-of-8
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Umbra V3 MoE 4x11b

Best Alternatives
Context / RAM
Downloads
Likes
Umbra V3 MoE 4x11b 2ex32K / 72.3 GB2864
PiVoT MoE32K / 72.3 GB17908
Umbra V3 MoE 4x11b 2ex32K / 72.3 GB54
Umbra V2.1 MoE 4x10.732K / 72.3 GB66
Mixolar 4x7b4K / 72.3 GB97803
Smartsolmix 4x10.7B V14K / 72.3 GB18580
Orca SOLAR 4x10.7B4K / 72.3 GB17380
MetaModel MoE4K / 72.3 GB19140
SOLARC MoE 10.7Bx44K / 144.7 GB19179
Frankenstein MoE En 10.7Bx44K / 72.3 GB19150
Note: green Score (e.g. "73.2") means that the model is better than SteelStorage/Umbra-v3-MoE-4x11b.

Rank the Umbra V3 MoE 4x11b 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? 51535 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