What are the hardware requirements for Airoboros L2 13B 2 1 YaRN 64K AWQ?

Airoboros L2 13B 2 1 YaRN 64K AWQ requires approximately 7.2 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Airoboros L2 13B 2 1 YaRN 64K AWQ and how large is it?

Airoboros L2 13B 2 1 YaRN 64K AWQ is developed by TheBloke, a model with 13b 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 Airoboros L2 13B 2 1 YaRN 64K AWQ?

Airoboros L2 13B 2 1 YaRN 64K AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Airoboros L2 13B 2 1 YaRN 64K AWQ by TheBloke — VRAM 7.2GB, 64K context

Name: Airoboros L2 13B 2 1 YaRN 64K AWQ
Author: TheBloke

Airoboros L2 13B 2 1 YaRN 64K AWQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.2GB, Context: 64K, License: llama2, Quantized, LLM Explorer Score: 0.09.

4-bit Awq Base model:bhenrym14/airoboros... Base model:quantized:bhenrym14... Custom code Dataset:jondurbin/airoboros-2.... Llama Quantized Region:us Safetensors Yarn

Model Card on HF 🤗: https://huggingface.co/TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-AWQ

Airoboros L2 13B 2 1 YaRN 64K AWQ Parameters and Internals

Model Type

llama

Additional Notes

To use with Transformers, pass trust_remote_code=True. Performance at long context lengths needs further exploration.

Training Details

Data Sources:

jondurbin/airoboros-2.1

Methodology:

Instruction tuning with additional pretraining done with YaRN scaling.

Context Length:

65536

Training Time:

~16 hours

Hardware Used:

1x RTX 6000 Ada

Model Architecture:

Extended context finetune of Llama-2-13b using YaRN scaling.

Input Output

Input Format:

A chat.\nUSER: {prompt}\nASSISTANT: \n

LLM Name	Airoboros L2 13B 2 1 YaRN 64K AWQ
Repository 🤗	https://huggingface.co/TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-AWQ
Model Name	Airoboros L2 13B 2.1 YaRN 64K
Model Creator	bhenrym14
Base Model(s)	bhenrym14/airoboros-l2-13b-2.1-YaRN-64k bhenrym14/airoboros-l2-13b-2.1-YaRN-64k
Model Size	13b
Required VRAM	7.2 GB
Updated	2026-08-02
Maintainer	TheBloke
Model Type	llama
Model Files	7.2 GB
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	65536
Model Max Length	65536
Transformers Version	4.33.0.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 Airoboros L2 13B 2 1 YaRN 64K 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 Airoboros L2 13B 2 1 YaRN 64K AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Yarn Llama 2 13B 128K AWQ	128K / 7.2 GB	4	2
LongAlign 13B 64K AWQ	64K / 7.2 GB	4	2
OrcaMaid V3 13B 32K AWQ	32K / 7.2 GB	5	4
OrcaMaid V2 FIX 13B 32K AWQ	32K / 7.2 GB	7	1
NexusRaven V2 13B AWQ	16K / 7.2 GB	11	3
NexusRaven V2 13B AWQ	16K / 7.2 GB	1	3
...th CodeLlama 13B Python Hf AWQ	16K / 7.5 GB	6	0
WhiteRabbitNeo 13B AWQ	16K / 7.2 GB	332	4
NexusRaven V2 13B AWQ	16K / 7.2 GB	10	1
Ramgpt 13B AWQ Gemm	16K / 7.2 GB	0	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-AWQ.