What are the hardware requirements for Yarn Llama 2 13B 128K GPTQ?

Yarn Llama 2 13B 128K GPTQ requires approximately 7.3 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Yarn Llama 2 13B 128K GPTQ and how large is it?

Yarn Llama 2 13B 128K GPTQ 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 Yarn Llama 2 13B 128K GPTQ?

Yarn Llama 2 13B 128K GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Yarn Llama 2 13B 128K GPTQ by TheBloke — VRAM 7.3GB, 128K context

Name: Yarn Llama 2 13B 128K GPTQ
Author: TheBloke

Yarn Llama 2 13B 128K GPTQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.3GB, Context: 128K, License: llama2, Quantized, LLM Explorer Score: 0.08.

Arxiv:2309.00071 4-bit Base model:nousresearch/yarn-l... Base model:quantized:nousresea... Custom code Dataset:pg19 Gptq Llama Quantized Region:us Safetensors Yarn

Model Card on HF 🤗: https://huggingface.co/TheBloke/Yarn-Llama-2-13B-128K-GPTQ

Yarn Llama 2 13B 128K GPTQ Parameters and Internals

Model Type

llama

Additional Notes

The model requires the Flash Attention library to function correctly.

Training Details

Data Sources:

pg19

Methodology:

Further pretrained on a subset of the PG19 dataset, allowing it to effectively utilize up to 128k tokens of context.

Context Length:

128000

Model Architecture:

Flash Attention 2 patched version

Input Output

Input Format:

{prompt}

LLM Name	Yarn Llama 2 13B 128K GPTQ
Repository 🤗	https://huggingface.co/TheBloke/Yarn-Llama-2-13B-128K-GPTQ
Model Name	Yarn Llama 2 13B 128K
Model Creator	NousResearch
Base Model(s)	Yarn Llama 2 13B 128K NousResearch/Yarn-Llama-2-13b-128k
Model Size	13b
Required VRAM	7.3 GB
Updated	2026-07-17
Maintainer	TheBloke
Model Type	llama
Model Files	7.3 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	131072
Model Max Length	131072
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	bfloat16

Rank the Yarn Llama 2 13B 128K GPTQ 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 Yarn Llama 2 13B 128K GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
LongAlign 13B 64K GPTQ	64K / 7.3 GB	5	1
...boros L2 13B 2 1 YaRN 64K GPTQ	64K / 7.3 GB	6	3
Yarn Llama 2 13B 64K GPTQ	64K / 7.3 GB	20	1
OrcaMaid V3 13B 32K GPTQ	32K / 7.3 GB	13	3
OrcaMaid V2 FIX 13B 32K GPTQ	32K / 7.3 GB	12	4
EverythingLM 13B 16K GPTQ	16K / 7.3 GB	70	14
LlongOrca 13B 16K GPT	16K / 7.3 GB	5	0
Tinybra 13B GPTQ 32g 4BIT	16K / 8 GB	3	1
Tinybra 13B GPTQ 4BIT	16K / 7 GB	5	0
WhiteRabbitNeo 13B GPTQ	16K / 7.3 GB	50	4

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Yarn-Llama-2-13B-128K-GPTQ.