What are the hardware requirements for Llama2 22B?

Llama2 22B requires approximately 43.7 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 and how large is it?

Llama2 22B is developed by chargoddard, 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 perform on standard benchmarks?

Llama2 22B has the following published scores: MMLU 54.68. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama2 22B by chargoddard — VRAM 43.7GB, 4K context

Name: Llama2 22B
Author: chargoddard

Llama2 22B is an open-source language model by chargoddard. Features: 22b LLM, VRAM: 43.7GB, Context: 4K, LLM Explorer Score: 0.11, Arc: 58.5, HellaSwag: 82.6, MMLU: 54.7, GSM8K: 9.9.

Dataset:togethercomputer/redpa... Deploy:azure Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/chargoddard/llama2-22b

Llama2 22B Parameters and Internals

Model Type

text-generation

Use Cases

Considerations:

Not intended for use as-is; meant for further tuning for enhanced learning capacity

Training Details

Data Sources:

togethercomputer/RedPajama-Data-1T-Sample

Data Volume:

~10M tokens

Methodology:

Transplantation of attention heads from Llama 33b, with fine-tuning

Model Architecture:

Enhanced Llama 13b model with additional attention heads from Llama 33b

LLM Name	Llama2 22B
Repository 🤗	https://huggingface.co/chargoddard/llama2-22b
Model Size	22b
Required VRAM	43.7 GB
Updated	2026-07-27
Maintainer	chargoddard
Model Type	llama
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 Architecture	LlamaForCausalLM
Context Length	4098
Model Max Length	4098
Transformers Version	4.32.0.dev0
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 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

Best Alternatives	Context / RAM	Downloads	Likes
EuroLLM 22B Instruct 2512	32K / 45.5 GB	3342	63
EuroLLM 22B 2512	32K / 45.5 GB	2766	19
Calm3 22B Chat	16K / 44.9 GB	878	85
Calm3 22B RP V2	16K / 44.9 GB	18	20
Calm3 22B RP V0.1	16K / 44.9 GB	8	0
Yousei 22B	4K / 44.5 GB	97	2
Llama2 22B Daydreamer V3	4K / 43.7 GB	177	11
Platypus 2 22B Relora	4K / 43.7 GB	93	1
Llama2 22B Blocktriangular	4K / 43.7 GB	368	4
Llama2 22B Daydreamer V2	4K / 43.7 GB	7	2

Note: green Score (e.g. "73.2") means that the model is better than chargoddard/llama2-22b.