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

K2S3 Mistral 7bx2 48layers V1.2 by Changgil

 »  All LLMs  »  Changgil  »  K2S3 Mistral 7bx2 48layers V1.2   URL Share it on

  103   

K2S3 Mistral 7bx2 48layers V1.2 is an open-source language model by Changgil. Features: 10.9b LLM, VRAM: 21.7GB, Context: 32K, License: cc-by-nc-4.0, MoE, LLM Explorer Score: 0.14, Arc: 56.3, HellaSwag: 77.8, MMLU: 57.9, GSM8K: 49.8.

  En   Endpoints compatible   Ko   Mistral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Changgil/K2S3-Mistral-7bx2-48layers_v1.2 

K2S3 Mistral 7bx2 48layers V1.2 Benchmarks

ARC: 56.31 vs 96.7 (so35)-41.8%
HellaSwag: 77.83 vs 95.3 (gpt4)-18.3%
MMLU: 57.91 vs 88.3 (so35)-34.4%
GSM8K: 49.81 vs 96.4 (so35)-48.3%
LLME Score: 0.14378
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
K2S3 Mistral 7bx2 48layers V1.2 (Changgil/K2S3-Mistral-7bx2-48layers_v1.2)
🌟 Advertise your project 🚀

K2S3 Mistral 7bx2 48layers V1.2 Parameters and Internals

Additional Notes 
Merge method uses dtype bfloat16 with passthrough merge method.
Supported Languages 
en (proficient), ko (proficient)
LLM NameK2S3 Mistral 7bx2 48layers V1.2
Repository 🤗https://huggingface.co/Changgil/K2S3-Mistral-7bx2-48layers_v1.2 
Model Size10.9b
Required VRAM21.7 GB
Updated2026-05-14
MaintainerChanggil
Model Typemistral
Model Files  5.0 GB: 1-of-5   4.9 GB: 2-of-5   5.0 GB: 3-of-5   4.9 GB: 4-of-5   1.9 GB: 5-of-5
Supported Languagesen ko
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.38.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size48000
Torch Data Typefloat16

Best Alternatives to K2S3 Mistral 7bx2 48layers V1.2

Best Alternatives
Context / RAM
Downloads
Likes
Krutrim 2 Instruct1000K / 49.3 GB25836
Ft V1 Violet1000K / 24.5 GB50
Mistral Large Instruct 2407128K / 226.7 GB7270860
Tiny Random MistralForCausalLM128K / 0 GB9051
Winterreise M732K / 14.4 GB00
Frostwind V2.1 M732K / 14.4 GB00
K2S3 V0.132K / 28.7 GB70
MistralLite32K / 14.4 GB10607434
MistralLite32K / 14.4 GB61777430
...ydaz Web AI Reasoner BaseModel32K / 14.4 GB01
Note: green Score (e.g. "73.2") means that the model is better than Changgil/K2S3-Mistral-7bx2-48layers_v1.2.

Rank the K2S3 Mistral 7bx2 48layers V1.2 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