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

Yarn Llama 2 13B 128K GGML requires approximately 5.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Yarn Llama 2 13B 128K GGML 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 GGML?

Yarn Llama 2 13B 128K GGML 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 GGML by TheBloke — VRAM 5.5GB

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

Yarn Llama 2 13B 128K GGML is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.5GB, License: llama2, Quantized, LLM Explorer Score: 0.09.

Arxiv:2309.00071 Base model:finetune:nousresear... Base model:nousresearch/yarn-l... Dataset:pg19 Ggml Llama Quantized Region:us Yarn

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

Yarn Llama 2 13B 128K GGML Benchmarks

LLME Score: 0.09077

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Yarn Llama 2 13B 128K GGML (TheBloke/Yarn-Llama-2-13B-128K-GGML)

🌟 Advertise your project 🚀

Yarn Llama 2 13B 128K GGML Parameters and Internals

Model Type

llama

Training Details

Data Sources:

PG19 dataset

Methodology:

Further pretrained on long context data for 600 steps

LLM Name	Yarn Llama 2 13B 128K GGML
Repository 🤗	https://huggingface.co/TheBloke/Yarn-Llama-2-13B-128K-GGML
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	5.5 GB
Updated	2026-04-22
Maintainer	TheBloke
Model Type	llama
Model Files	5.5 GB 6.9 GB 6.3 GB 5.7 GB 7.4 GB 8.2 GB 7.9 GB 7.4 GB 9.0 GB 9.8 GB 9.2 GB 9.0 GB 10.7 GB 13.8 GB
GGML Quantization	Yes
Quantization Type	ggml
Model Architecture	AutoModel
License	llama2

Best Alternatives to Yarn Llama 2 13B 128K GGML

Best Alternatives	Context / RAM	Downloads	Likes
Llama 2 13B Chat GGML	0K / 5.5 GB	637	695
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	8
Llama 2 13B GGML	0K / 5.5 GB	507	174
RuGPT 3.5 13B GGML	0K / 7.4 GB	4	15
...rca Platypus WizardLM 13B GGML	0K / 5.5 GB	12	6
...penBuddy Llama2 13B V11.1 GGML	0K / 5.5 GB	1	5
Speechless Llama2 13B GGML	0K / 5.5 GB	9	2
CodeLlama 13B GGML	0K / 5.7 GB	21	33
Yarn Llama 2 13B 64K GGML	0K / 5.5 GB	4	5
UndiMix V1 13B GGML	0K / 5.5 GB	15	1

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

Rank the Yarn Llama 2 13B 128K GGML Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53205 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Yarn Llama 2 13B 128K GGML by TheBloke

» All LLMs » TheBloke » Yarn Llama 2 13B 128K GGML URL Share it on

Yarn Llama 2 13B 128K GGML Benchmarks

Yarn Llama 2 13B 128K GGML Parameters and Internals

Best Alternatives to Yarn Llama 2 13B 128K GGML

Rank the Yarn Llama 2 13B 128K GGML Capabilities

What open-source LLMs or SLMs are you in search of? 53205 in total.