What are the hardware requirements for Llama2 22B Daydreamer V3 GPT?

Llama2 22B Daydreamer V3 GPT requires approximately 12 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama2 22B Daydreamer V3 GPT and how large is it?

Llama2 22B Daydreamer V3 GPT is developed by aegon-h, a model with 22b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama2 22B Daydreamer V3 GPT perform on standard benchmarks?

Llama2 22B Daydreamer V3 GPT has the following published scores: MMLU 52.49. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama2 22B Daydreamer V3 GPT by aegon-h — VRAM 12GB, 4K context

Name: Llama2 22B Daydreamer V3 GPT
Author: aegon-h

Llama2 22B Daydreamer V3 GPT is an open-source language model by aegon-h. Features: 22b LLM, VRAM: 12GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.11, Arc: 56.1, HellaSwag: 80.1, MMLU: 52.5, GSM8K: 3.8.

4-bit Gptq Llama Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/aegon-h/Llama2-22B-Daydreamer-v3-GPT

Llama2 22B Daydreamer V3 GPT Parameters and Internals

Model Type

llama

LLM Name	Llama2 22B Daydreamer V3 GPT
Repository 🤗	https://huggingface.co/aegon-h/Llama2-22B-Daydreamer-v3-GPT
Model Name	Llama2 22B Daydreamer2 v3
Model Creator	Nick Perez
Base Model(s)	Llama2 22B Daydreamer V3 nkpz/llama2-22b-daydreamer-v3
Model Size	22b
Required VRAM	12 GB
Updated	2026-06-07
Maintainer	aegon-h
Model Type	llama
Model Files	10.0 GB: 1-of-2 2.0 GB: 2-of-2
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4098
Model Max Length	4098
Transformers Version	4.32.1
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Llama2 22B Daydreamer V3 GPT capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Llama2 22B Daydreamer V3 GPT

Best Alternatives	Context / RAM	Downloads	Likes
Llama2 22B Daydreamer V3 GPTQ	4K / 12 GB	10	6
Llama2 22B Daydreamer V2 GPTQ	4K / 12 GB	8	8
Ypotryll 22B Gptq	4K / 12 GB	9	1
Llama2 22B GPLATTY GPT	4K / 12 GB	6	0
Huginn 22B Prototype GPTQ	4K / 12 GB	2	1
Llama2 22B GPLATTY GPTQ	4K / 12 GB	4	4
Nucleus 22B Token 500B GPTQ	2K / 11.6 GB	7	2
...LLM 22B Instruct 2512 Mlx 4bit	32K / 12.7 GB	127	3
...LLM 22B Instruct 2512 Mlx 8bit	32K / 24.1 GB	53	1
Dendrite 22Bchk2 F16	4K / 43.7 GB	7	1

Note: green Score (e.g. "73.2") means that the model is better than aegon-h/Llama2-22B-Daydreamer-v3-GPT.