What are the hardware requirements for Nucleus 22B Token 500B AWQ?

Nucleus 22B Token 500B AWQ requires approximately 12 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nucleus 22B Token 500B AWQ and how large is it?

Nucleus 22B Token 500B AWQ is developed by TheBloke, a model with 22b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Nucleus 22B Token 500B AWQ?

Nucleus 22B Token 500B AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nucleus 22B Token 500B AWQ by TheBloke — VRAM 12GB, 2K context

Name: Nucleus 22B Token 500B AWQ
Author: TheBloke

Nucleus 22B Token 500B AWQ is an open-source language model by TheBloke. Features: 22b LLM, VRAM: 12GB, Context: 2K, License: mit, Quantized, LLM Explorer Score: 0.1.

4-bit Awq Base model:nucleusai/nucleus-2... Base model:quantized:nucleusai... En Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/nucleus-22B-token-500B-AWQ

Nucleus 22B Token 500B AWQ Parameters and Internals

Model Type

causal decoder-only

Additional Notes

Model is quantized by TheBloke using low-bit weight quantization method, AWQ.

Supported Languages

en (high)

Training Details

Data Sources:

RefinedWeb-English, Books, Code, Technical, Math

Data Volume:

500B tokens

Context Length:

2048

Training Time:

about two weeks

Hardware Used:

256 A100 80GB GPUs

Input Output

Input Format:

{prompt}

LLM Name	Nucleus 22B Token 500B AWQ
Repository 🤗	https://huggingface.co/TheBloke/nucleus-22B-token-500B-AWQ
Model Name	Nucleus 22B Token 500B
Model Creator	NucleusAI
Base Model(s)	Nucleus 22B Token 500B NucleusAI/nucleus-22B-token-500B
Model Size	22b
Required VRAM	12 GB
Updated	2026-05-26
Maintainer	TheBloke
Model Type	llama
Model Files	10.0 GB: 1-of-2 2.0 GB: 2-of-2
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.2
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 Nucleus 22B Token 500B AWQ 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 Nucleus 22B Token 500B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Llama2 22B Daydreamer V3 AWQ	4K / 12 GB	4	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
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	21	20
Calm3 22B RP V0.1	16K / 44.9 GB	10	0
Yousei 22B	4K / 44.5 GB	97	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/nucleus-22B-token-500B-AWQ.