What are the hardware requirements for Speechless Llama2 13B GGML?

Speechless Llama2 13B 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 Speechless Llama2 13B GGML and how large is it?

Speechless Llama2 13B 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 Speechless Llama2 13B GGML?

Speechless Llama2 13B GGML is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Speechless Llama2 13B GGML by TheBloke — VRAM 5.5GB

Name: Speechless Llama2 13B GGML
Author: TheBloke

Speechless Llama2 13B GGML is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.5GB, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.08.

Arxiv:2307.09288 Base model:finetune:uukuguy/sp... Base model:uukuguy/speechless-... Dataset:garage-baind/open-plat... Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol... En Facebook Ggml Instruct Llama Llama2 Meta Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/TheBloke/Speechless-Llama2-13B-GGML

Speechless Llama2 13B GGML Parameters and Internals

Model Type

llama

Use Cases

Areas:

Research, Commercial applications

Applications:

Text generation, Dialogue systems

Primary Use Cases:

Chatbot development, Natural language generation tasks

Limitations:

Tested primarily in English, may not cover all scenarios

Considerations:

Developers should perform safety testing tailored to their specific applications.

Additional Notes

Llama 2 was trained between January 2023 and July 2023.

Training Details

Data Sources:

Open-Orca/OpenOrca, garage-bAInd/Open-Platypus, WizardLM/WizardLM_evol_instruct_V2_196k

Data Volume:

2 trillion tokens

Methodology:

Merge of Open-Orca/OpenOrca-Platypus2-13B and WizardLM/WizardLM-13B-V1.2

Context Length:

4096

Hardware Used:

A100-80GB GPUs

Model Architecture:

Optimized transformer architecture with fine-tuning using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)

Input Output

Input Format:

Text

Accepted Modalities:

text

Output Format:

Text

Performance Tips:

Use GGUF files for compatibility with latest llama.cpp for optimal performance.

Release Notes

Version:

v1.1

Notes:

A merge of Open-Orca/OpenOrca-Platypus2-13B and WizardLM/WizardLM-13B-V1.2.

LLM Name	Speechless Llama2 13B GGML
Repository 🤗	https://huggingface.co/TheBloke/Speechless-Llama2-13B-GGML
Model Name	Speechless Llama2 13B
Model Creator	Jiangwen Su
Base Model(s)	Speechless Llama2 13B uukuguy/speechless-llama2-13b
Model Size	13b
Required VRAM	5.5 GB
Updated	2026-07-25
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
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
Supported Languages	en
GGML Quantization	Yes
Quantization Type	ggml
Model Architecture	AutoModel
License	llama2

Rank the Speechless Llama2 13B 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 Speechless Llama2 13B GGML

Best Alternatives	Context / RAM	Downloads	Likes
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	8
CodeLlama 13B Instruct GGML	0K / 5.7 GB	11	19
...lama2 13B Orca V2 8K 3166 GGML	0K / 5.7 GB	4	14
Vigogne 2 13B Instruct GGML	0K / 5.5 GB	5	6
...1.0 Uncensored Llama2 13B GGML	0K / 5.5 GB	6	60
Llama 3 13B Instruct V0.1 GGUF	0K / 5.1 GB	1940	5
...aMa 3 Instruct Zeroed 13B GGUF	0K / 5 GB	42	1
Codellama 7B Instruct GGUF	0K / 2.8 GB	166	1
Codellama 13B Instruct GGUF	0K / 13.8 GB	28	0
Finance LLM 13B GGUF	0K / 4.8 GB	516	21

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Speechless-Llama2-13B-GGML.