Vicuna 7B V1.5 GGML by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Vicuna 7B V1.5 GGML   URL Share it on

Vicuna 7B V1.5 GGML is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 2.9GB, License: llama2, Quantized, LLM Explorer Score: 0.09.

  Arxiv:2306.05685   Arxiv:2307.09288 Base model:finetune:lmsys/vicu... Base model:lmsys/vicuna-7b-v1....   Ggml   Llama   Quantized   Region:us

Vicuna 7B V1.5 GGML Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Vicuna 7B V1.5 GGML (TheBloke/vicuna-7B-v1.5-GGML)
๐ŸŒŸ Advertise your project ๐Ÿš€

Vicuna 7B V1.5 GGML Parameters and Internals

Model Type 
auto-regressive, transformer architecture
Use Cases 
Areas:
Research on large language models and chatbots
Applications:
Natural language processing, machine learning, artificial intelligence
Additional Notes 
GGML format has been superseded by GGUF. For compatibility with the latest llama.cpp, use GGUF files.
Training Details 
Data Sources:
ShareGPT.com
Data Volume:
125K conversations
Methodology:
Supervised instruction fine-tuning
LLM NameVicuna 7B V1.5 GGML
Repository ๐Ÿค—https://huggingface.co/TheBloke/vicuna-7B-v1.5-GGML 
Model NameVicuna 7B v1.5
Model Creatorlmsys
Base Model(s)  lmsys/vicuna-7b-v1.5   lmsys/vicuna-7b-v1.5
Model Size7b
Required VRAM2.9 GB
Updated2025-12-31
MaintainerTheBloke
Model Typellama
Model Files  2.9 GB   3.6 GB   3.3 GB   3.0 GB   3.8 GB   4.2 GB   4.1 GB   3.8 GB   4.7 GB   5.1 GB   4.8 GB   4.7 GB   5.5 GB   7.1 GB
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Vicuna 7B V1.5 GGML

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 7B Chat GGML0K / 2.9 GB355872
Llama 2 GGML Medical Chatbot0K /  GB945
Llama 2 7B GGML0K / 2.9 GB118219
CodeLlama 7B GGML0K / 3 GB1427
Yarn Llama 2 7B 128K GGML0K / 2.9 GB56
CodeLlama 7B Instruct GGML0K / 3 GB2820
CodeLlama 7B Python GGML0K / 2.9 GB724
Yarn Llama 2 7B 64K GGML0K / 2.9 GB13
Airoboros L2 7B 2.1 GGML0K / 2.9 GB31
Zarafusionex 1.1 L2 7B GGML0K / 2.9 GB12
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/vicuna-7B-v1.5-GGML.

Rank the Vicuna 7B V1.5 GGML Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52392 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a