What are the hardware requirements for Llama 2 13B Chat GGML?

Llama 2 13B Chat 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 Llama 2 13B Chat GGML and how large is it?

Llama 2 13B Chat 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 Llama 2 13B Chat GGML?

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

Llama 2 13B Chat GGML by TheBloke — VRAM 5.5GB

Name: Llama 2 13B Chat GGML
Author: TheBloke

Llama 2 13B Chat GGML is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.5GB, License: other, Quantized, LLM Explorer Score: 0.1.

Arxiv:2307.09288 Base model:finetune:meta-llama... Base model:meta-llama/llama-2-... En Facebook Ggml Llama Llama2 Meta Pytorch Quantized Region:us

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

Llama 2 13B Chat GGML Parameters and Internals

Model Type

llama

Use Cases

Areas:

commercial, research

Applications:

assistant-like chat, natural language generation tasks

Primary Use Cases:

optimized for dialogue use cases

Limitations:

Inaccurate, biased or other objectionable responses possible; testing primarily in English

Considerations:

Perform safety testing and tuning tailored to specific applications

Training Details

Data Sources:

publicly available online data

Data Volume:

2.0 trillion tokens

Methodology:

Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)

Context Length:

4000

Hardware Used:

Meta's Research Super Cluster, A100-80GB GPUs

Model Architecture:

Optimized transformer architecture

Input Output

Input Format:

Text input only

Accepted Modalities:

text

Output Format:

Text output only

Performance Tips:

A specific formatting, including `INST`, `<>`, `BOS`, and `EOS` tokens, is required for optimal performance

LLM Name	Llama 2 13B Chat GGML
Repository 🤗	https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML
Model Name	Llama 2 13B Chat
Model Creator	Meta Llama 2
Base Model(s)	Llama 2 13B Chat Hf meta-llama/Llama-2-13b-chat-hf
Model Size	13b
Required VRAM	5.5 GB
Updated	2026-08-01
Maintainer	TheBloke
Model Type	llama
Model Files	5.5 GB 6.9 GB 6.3 GB 5.7 GB 7.3 GB 8.1 GB 7.9 GB 7.4 GB 8.9 GB 9.8 GB 9.2 GB 9.0 GB 10.7 GB 13.8 GB
Supported Languages	en
GGML Quantization	Yes
Quantization Type	ggml
Model Architecture	AutoModel
License	other

Rank the Llama 2 13B Chat GGML 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 Llama 2 13B Chat GGML

Best Alternatives	Context / RAM	Downloads	Likes
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	8
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	15
...penBuddy Llama2 13B V11.1 GGML	0K / 5.5 GB	11	5
...rca Platypus WizardLM 13B GGML	0K / 5.5 GB	6	6
Yarn Llama 2 13B 128K GGML	0K / 5.5 GB	5	6
Yarn Llama 2 13B 64K GGML	0K / 5.5 GB	7	5
Stheno L2 13B GGML	0K / 5.5 GB	7	5
Speechless Llama2 13B GGML	0K / 5.5 GB	4	2
Asclepius 13B GGML	0K / 5.5 GB	6	1
CodeLlama 13B GGML	0K / 5.7 GB	11	33