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

Llama2 22B Daydreamer V3 by nkpz

 »  All LLMs  »  nkpz  »  Llama2 22B Daydreamer V3   URL Share it on

  340   

Llama2 22B Daydreamer V3 is an open-source language model by nkpz. Features: 22b LLM, VRAM: 43.7GB, Context: 4K, License: other, LLM Explorer Score: 0.12, Arc: 56.1, HellaSwag: 80.1, MMLU: 52.5, GSM8K: 3.8.

  Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/nkpz/llama2-22b-daydreamer-v3 

Llama2 22B Daydreamer V3 Benchmarks

ARC: 56.06 vs 96.7 (so35)-42%
HellaSwag: 80.07 vs 95.3 (gpt4)-16%
MMLU: 52.49 vs 88.3 (so35)-40.6%
GSM8K: 3.79 vs 96.4 (so35)-96.1%
LLME Score: 0.11547
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama2 22B Daydreamer V3 (nkpz/llama2-22b-daydreamer-v3)
🌟 Advertise your project 🚀

Llama2 22B Daydreamer V3 Parameters and Internals

Model Type 
Roleplay, Q&A, Instruction Following, Conversational
Use Cases 
Areas:
Roleplay, Instruction following, Conversational applications
Additional Notes 
Model has been enhanced to roleplay and imitate speech styles effectively. Exhibits a dry and accurate response style for informational queries but is also capable of delivering playful responses for casual prompts.
Supported Languages 
English (Proficient)
Training Details 
Data Sources:
Instruction data, Roleplay data, Conversational data, Jondurbin Airoboros GPT4 1.4.1 MPT Dataset excluding coding rows
Hardware Used:
NVIDIA 3090
Input Output 
Accepted Modalities:
Text
LLM NameLlama2 22B Daydreamer V3
Repository 🤗https://huggingface.co/nkpz/llama2-22b-daydreamer-v3 
Model Size22b
Required VRAM43.7 GB
Updated2026-07-02
Maintainernkpz
Model Typellama
Model Files  9.8 GB: 1-of-5   10.0 GB: 2-of-5   9.9 GB: 3-of-5   9.9 GB: 4-of-5   4.1 GB: 5-of-5
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4098
Model Max Length4098
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Llama2 22B Daydreamer V3

Model
Likes
Downloads
VRAM
Llama2 22B Daydreamer V3 GPT0712 GB
Llama2 22B Daydreamer V3 GGUF24129 GB
Llama2 22B Daydreamer V3 AWQ21112 GB
Llama2 22B Daydreamer V3 GPTQ61112 GB
Llama2 22B Daydreamer V3 GGML659 GB

Best Alternatives to Llama2 22B Daydreamer V3

Best Alternatives
Context / RAM
Downloads
Likes
EuroLLM 22B Instruct 251232K / 45.5 GB334263
Calm3 22B Chat16K / 44.9 GB51685
Calm3 22B RP V216K / 44.9 GB7120
Calm3 22B RP V0.116K / 44.9 GB70
Yousei 22B4K / 44.5 GB1822
Llama2 22B Blocktriangular4K / 43.7 GB8784
Platypus 2 22B Relora4K / 43.7 GB2091
Llama2 22B4K / 43.7 GB15446
Llama2 22B Daydreamer V24K / 43.7 GB112
Llama2 22B Daydreamer V14K / 43.7 GB62
Note: green Score (e.g. "73.2") means that the model is better than nkpz/llama2-22b-daydreamer-v3.

Rank the Llama2 22B Daydreamer V3 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? 54931 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