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

OPT 6.7B Nerybus Mix by KoboldAI

 »  All LLMs  »  KoboldAI  »  OPT 6.7B Nerybus Mix   URL Share it on

  1869   

OPT 6.7B Nerybus Mix is an open-source language model by KoboldAI. Features: 6.7b LLM, VRAM: 13.7GB, Context: 2K, License: other, HF Score: 38.8, LLM Explorer Score: 0.11, Arc: 39.2, HellaSwag: 68.6, MMLU: 24.5, TruthfulQA: 34.8, WinoGrande: 65.1, GSM8K: 0.8.

  Autotrain compatible   En   Opt   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/KoboldAI/OPT-6.7B-Nerybus-Mix 

OPT 6.7B Nerybus Mix Benchmarks

ARC: 39.16 vs 96.7 (so35)-59.5%
HellaSwag: 68.63 vs 95.3 (gpt4)-28%
MMLU: 24.47 vs 88.3 (so35)-72.3%
TruthfulQA: 34.84 vs 59 (gpt4)-40.9%
WinoGrande: 65.11 vs 87.5 (gpt4)-25.6%
GSM8K: 0.76 vs 96.4 (so35)-99.2%
LLME Score: 0.11307
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OPT 6.7B Nerybus Mix (KoboldAI/OPT-6.7B-Nerybus-Mix)
🌟 Advertise your project 🚀

OPT 6.7B Nerybus Mix Parameters and Internals

Additional Notes 
This experimental model combines the weights of two source models with a parameter-wise 50/50 blend, producing coherent outputs though less impressive than the 2.7B variant.
LLM NameOPT 6.7B Nerybus Mix
Repository 🤗https://huggingface.co/KoboldAI/OPT-6.7B-Nerybus-Mix 
Model Size6.7b
Required VRAM13.7 GB
Updated2025-09-23
MaintainerKoboldAI
Model Typeopt
Model Files  3.1 GB: 1-of-5   3.1 GB: 2-of-5   3.1 GB: 3-of-5   3.0 GB: 4-of-5   1.4 GB: 5-of-5
Supported Languagesen
Model ArchitectureOPTForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.24.0
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token</s>
End of Sentence Token</s>
Unk Token</s>
Vocabulary Size50265
Torch Data Typefloat16
Activation Functionrelu
Errorsreplace

Best Alternatives to OPT 6.7B Nerybus Mix

Best Alternatives
Context / RAM
Downloads
Likes
...7B Gqa Ub 16 Best For KV Cache2K / 27.4 GB2280
....7B Qcqa Ub 16 Best For Q Loss2K / 27.4 GB1670
Galactica 6.7B ReFT GSM8k2K / 13.8 GB4020
...B Qcqa Ub 16 Best For KV Cache2K / 27.4 GB400
Galactica 6.7B EssayWriter2K / 13.4 GB7565
Opt Flan Iml 6.7B2K / 26.6 GB8161
...lactica 6.7B Evol Instruct 70K2K / 27.4 GB42819
Galactica 6.7B Finetuned2K / 27.4 GB80834
Opt 6.7B2K / 13.4 GB29716118
OPT 6.7B Erebus2K / 13.3 GB209498
Note: green Score (e.g. "73.2") means that the model is better than KoboldAI/OPT-6.7B-Nerybus-Mix.

Rank the OPT 6.7B Nerybus Mix 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? 52394 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