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

Llama3.1 8B Spaetzle V59 by cstr

 »  All LLMs  »  cstr  »  Llama3.1 8B Spaetzle V59   URL Share it on

  1   
  Merged Model Base model:dampfinchen/llama-3... Base model:finetune:dampfinche... Dampfinchen/llama-3.1-8b-ultra...   De   En   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow Undi95/meta-llama-3.1-8b-claud...
Model Card on HF 🤗: https://huggingface.co/cstr/llama3.1-8b-spaetzle-v59 

Llama3.1 8B Spaetzle V59 Benchmarks

LLME Score: 0.1968
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3.1 8B Spaetzle V59 (cstr/llama3.1-8b-spaetzle-v59)

Llama3.1 8B Spaetzle V59 Parameters and Internals

Model Type 
text generation
Additional Notes 
Model is a merge of Undi95/Meta-Llama-3.1-8B-Claude and Dampfinchen/Llama-3.1-8B-Ultra-Instruct using dare_ties merge method.
Supported Languages 
en (English), de (German)
Training Details 
Methodology:
dare ties merge
Input Output 
Input Format:
Chat prompts
Accepted Modalities:
text
Output Format:
Generated text
LLM NameLlama3.1 8B Spaetzle V59
Repository 🤗https://huggingface.co/cstr/llama3.1-8b-spaetzle-v59 
Base Model(s)  Dampfinchen/Llama-3.1-8B-Ultra-Instruct   Dampfinchen/Llama-3.1-8B-Ultra-Instruct
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2025-05-15
Maintainercstr
Model Typellama
Instruction-BasedYes
Model Files  1.1 GB: 1-of-17   1.1 GB: 2-of-17   1.0 GB: 3-of-17   1.0 GB: 4-of-17   1.0 GB: 5-of-17   0.9 GB: 6-of-17   1.0 GB: 7-of-17   1.0 GB: 8-of-17   1.0 GB: 9-of-17   0.9 GB: 10-of-17   1.0 GB: 11-of-17   1.0 GB: 12-of-17   1.0 GB: 13-of-17   0.9 GB: 14-of-17   1.0 GB: 15-of-17   1.0 GB: 16-of-17   0.2 GB: 17-of-17
Supported Languagesen de
Model ArchitectureLlamaForCausalLM
Licensellama3.1
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama3.1 8B Spaetzle V59

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB5687104
UltraLong Thinking4192K / 16.1 GB2712
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB102715
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB499441
Zero Llama 3.1 8B Beta61048K / 16.1 GB1051
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB532
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB392
Note: green Score (e.g. "73.2") means that the model is better than cstr/llama3.1-8b-spaetzle-v59.

Rank the Llama3.1 8B Spaetzle V59 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? 47368 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