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

Naps Llama3.1 70B V0.2 Fp16 by NAPS-ai

 »  All LLMs  »  NAPS-ai  »  Naps Llama3.1 70B V0.2 Fp16   URL Share it on

  6   

Naps Llama3.1 70B V0.2 Fp16 is an open-source language model by NAPS-ai. Features: 70b LLM, VRAM: 142.4GB, Context: 128K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.18.

Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Fp16   Instruct   Ko   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NAPS-ai/naps-llama3.1-70B-v0.2-fp16 

Naps Llama3.1 70B V0.2 Fp16 Benchmarks

MMLU Pro: 1.1
MUSR: 2.68
BBH: 3.07
IFEval: 18.45 vs 88 (so35)-79%
LLME Score: 0.17755
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Naps Llama3.1 70B V0.2 Fp16 (NAPS-ai/naps-llama3.1-70B-v0.2-fp16)
🌟 Advertise your project 🚀

Naps Llama3.1 70B V0.2 Fp16 Parameters and Internals

LLM NameNaps Llama3.1 70B V0.2 Fp16
Repository 🤗https://huggingface.co/NAPS-ai/naps-llama3.1-70B-v0.2-fp16 
Base Model(s)  meta-llama/Llama-3.1-70B-Instruct   meta-llama/Llama-3.1-70B-Instruct
Model Size70b
Required VRAM142.4 GB
Updated2025-09-23
MaintainerNAPS-ai
Model Typellama
Instruction-BasedYes
Model Files  4.6 GB: 1-of-30   4.7 GB: 2-of-30   5.0 GB: 3-of-30   4.6 GB: 4-of-30   4.7 GB: 5-of-30   4.7 GB: 6-of-30   5.0 GB: 7-of-30   4.6 GB: 8-of-30   4.7 GB: 9-of-30   4.7 GB: 10-of-30   5.0 GB: 11-of-30   4.6 GB: 12-of-30   4.7 GB: 13-of-30   4.7 GB: 14-of-30   5.0 GB: 15-of-30   4.6 GB: 16-of-30   4.7 GB: 17-of-30   4.7 GB: 18-of-30   5.0 GB: 19-of-30   4.6 GB: 20-of-30   4.7 GB: 21-of-30   4.7 GB: 22-of-30   5.0 GB: 23-of-30   4.6 GB: 24-of-30   4.7 GB: 25-of-30   4.7 GB: 26-of-30   5.0 GB: 27-of-30   4.6 GB: 28-of-30   4.7 GB: 29-of-30   4.8 GB: 30-of-30
Supported Languagesko
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.45.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Naps Llama3.1 70B V0.2 Fp16

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB485
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB133
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB332
...0B Instruct Gradient 262K 4bit256K / 39.7 GB333
...0B Instruct Gradient 262K 8bit256K / 75 GB152
...0B Instruct Gradient 262K 2bit256K / 21.9 GB211
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB41
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB50

Rank the Naps Llama3.1 70B V0.2 Fp16 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? 53232 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