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

Llama 3.2 3B Kermes V2 by Nexesenex

 »  All LLMs  »  Nexesenex  »  Llama 3.2 3B Kermes V2   URL Share it on

  37   
  Merged Model   Arxiv:2403.19522   Autotrain compatible Base model:cognitivecomputatio... Base model:maziyarpanahi/calme... Base model:nexesenex/llama 3.2...   Conversational   Endpoints compatible   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Nexesenex/Llama_3.2_3b_Kermes_v2 

Llama 3.2 3b Kermes V2 Benchmarks

MMLU Pro: 19.27
GPQA: 2.01
MUSR: 4.66
BBH: 22.05
IFEval: 57.54 vs 88 (so35)-34.6%
MATH Lvl 5: 5.44
LLME Score: 0.30703
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.2 3B Kermes V2 (Nexesenex/Llama_3.2_3b_Kermes_v2)

Llama 3.2 3B Kermes V2 Parameters and Internals

LLM NameLlama 3.2 3b Kermes V2
Repository 🤗https://huggingface.co/Nexesenex/Llama_3.2_3b_Kermes_v2 
Base Model(s)  Nexesenex/Llama_3.2_3b_Kermes_0.2_bf16   cognitivecomputations/Dolphin3.0-Llama3.2-3B   MaziyarPanahi/calme-3.3-llamaloi-3b   Nexesenex/Llama_3.2_3b_Kermes_0.2_bf16   cognitivecomputations/Dolphin3.0-Llama3.2-3B   MaziyarPanahi/calme-3.3-llamaloi-3b
Merged ModelYes
Model Size3b
Required VRAM6.5 GB
Updated2025-03-18
MaintainerNexesenex
Model Typellama
Model Files  1.0 GB: 1-of-7   1.0 GB: 2-of-7   1.0 GB: 3-of-7   0.9 GB: 4-of-7   1.0 GB: 5-of-7   1.0 GB: 6-of-7   0.6 GB: 7-of-7
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.48.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3.2 3B Kermes V2

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB28817131227
Hermes 3 Llama 3.2 3B128K / 6.5 GB342805147
Llama 3.2 3B128K / 6.5 GB417733528
DeepSeek R1 Distill Llama 3B128K / 6.5 GB241810
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB432
Llama 3.2 3B ToxicKod128K / 6.4 GB612
ReasoningCore 3B RE1 V2128K / 6.5 GB2890
...penReasoner Llama 3.2 3B Rs1.0128K / 6.5 GB1991
Calme 3.1 Llamaloi 3B128K / 10.6 GB30211
Eximius Persona 5B128K / 11.6 GB4434
Note: green Score (e.g. "73.2") means that the model is better than Nexesenex/Llama_3.2_3b_Kermes_v2.

Rank the Llama 3.2 3B Kermes V2 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? 45269 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 v20241227
  Support LLM Explorer