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 GPTQ by TheBloke

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

  10   

Llama2 22B Daydreamer V3 GPTQ is an open-source language model by TheBloke. Features: 22b LLM, VRAM: 12GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.09.

  4-bit Base model:nkpz/llama2-22b-day... Base model:quantized:nkpz/llam...   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama2-22B-Daydreamer-v3-GPTQ 

Llama2 22B Daydreamer V3 GPTQ Benchmarks

LLME Score: 0.08645
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 GPTQ (TheBloke/Llama2-22B-Daydreamer-v3-GPTQ)
🌟 Advertise your project 🚀

Llama2 22B Daydreamer V3 GPTQ Parameters and Internals

Model Type 
llama
Additional Notes 
Model expanded to Llama 1 33B size in certain areas, with a focus on roleplay and conversational data. Trained to handle various input styles, especially the Alpaca format.
Training Details 
Data Sources:
https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1-mpt
Hardware Used:
3090
Model Architecture:
Llama2 expanded to Llama 1 33B size, filled with Llama 33B data and finetuned using large Loras.
Input Output 
Input Format:
Alpaca format
LLM NameLlama2 22B Daydreamer V3 GPTQ
Repository 🤗https://huggingface.co/TheBloke/Llama2-22B-Daydreamer-v3-GPTQ 
Model NameLlama2 22B Daydreamer2 v3
Model CreatorNick Perez
Base Model(s)  Llama2 22B Daydreamer V3   nkpz/llama2-22b-daydreamer-v3
Model Size22b
Required VRAM12 GB
Updated2026-05-14
MaintainerTheBloke
Model Typellama
Model Files  12.0 GB
GPTQ QuantizationYes
Quantization Typegptq
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

Best Alternatives to Llama2 22B Daydreamer V3 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Llama2 22B Daydreamer V3 GPT4K / 12 GB130
Llama2 22B Daydreamer V2 GPTQ4K / 12 GB148
Ypotryll 22B Gptq4K / 12 GB11
Llama2 22B GPLATTY GPT4K / 12 GB60
Huginn 22B Prototype GPTQ4K / 12 GB181
Llama2 22B GPLATTY GPTQ4K / 12 GB134
Nucleus 22B Token 500B GPTQ2K / 11.6 GB72
...LLM 22B Instruct 2512 Mlx 4bit32K / 12.7 GB783
Dendrite 22Bchk2 F164K / 43.7 GB61
EuroLLM 22B Instruct 251232K / 45.5 GB334263
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama2-22B-Daydreamer-v3-GPTQ.

Rank the Llama2 22B Daydreamer V3 GPTQ 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? 53972 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