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

Llama 3 Umievo Shizuko Sqlcoder 2x8B by keitokei1994

 »  All LLMs  »  keitokei1994  »  Llama 3 Umievo Shizuko Sqlcoder 2x8B   URL Share it on

  7   

Llama 3 Umievo Shizuko Sqlcoder 2x8B is an open-source language model by keitokei1994. Features: 13.7b LLM, VRAM: 27.4GB, Context: 8K, License: llama3, MoE, LLM Explorer Score: 0.14.

  Code   Conversational   En   Endpoints compatible   Ja   Mixtral   Moe   Region:us   Safetensors   Sharded   Sql   Tensorflow
Model Card on HF 🤗: https://huggingface.co/keitokei1994/Llama-3-Umievo-Shizuko-sqlcoder-2x8B 

Llama 3 Umievo Shizuko Sqlcoder 2x8B Benchmarks

LLME Score: 0.13819
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Umievo Shizuko Sqlcoder 2x8B (keitokei1994/Llama-3-Umievo-Shizuko-sqlcoder-2x8B)
🌟 Advertise your project 🚀

Llama 3 Umievo Shizuko Sqlcoder 2x8B Parameters and Internals

Model Type 
Mixture of Experts (MoE)
Use Cases 
Primary Use Cases:
Japanese language processing, SQL generation
Additional Notes 
It uses the Q4_K_M quantized model and is tested using Llama.cpp and LMstudio.
Supported Languages 
English (full proficiency), Japanese (full proficiency)
LLM NameLlama 3 Umievo Shizuko Sqlcoder 2x8B
Repository 🤗https://huggingface.co/keitokei1994/Llama-3-Umievo-Shizuko-sqlcoder-2x8B 
Model Size13.7b
Required VRAM27.4 GB
Updated2026-04-12
Maintainerkeitokei1994
Model Typemixtral
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   7.4 GB: 3-of-3
Supported Languagesja en
Model ArchitectureMixtralForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|begin_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 Umievo Shizuko Sqlcoder 2x8B

Best Alternatives
Context / RAM
Downloads
Likes
... Deepseek DeepHermes E32 13.7B128K / 54.9 GB50
HAI SER128K / 27.3 GB916
L3.1 Celestial Stone 2x8B128K / 27.3 GB3123
...ma 3 2x8B Instruct MoE 64K Ctx64K / 27.3 GB124
Penny Llama3 2x8b8K / 27.3 GB41
Kilo 2x8B8K / 27.5 GB121
Defne Llama3 2x8B8K / 27.4 GB146
Llama 3 Elyza Youko MoE 2x8B8K / 27.3 GB50
Llama 3 ELYZA Hermes 2x8B8K / 27.4 GB01
Inixion 2x8B V28K / 27.4 GB62
Note: green Score (e.g. "73.2") means that the model is better than keitokei1994/Llama-3-Umievo-Shizuko-sqlcoder-2x8B.

Rank the Llama 3 Umievo Shizuko Sqlcoder 2x8B 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? 52889 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