LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

LLaVA Meta Llama 3 8B Instruct by MBZUAI

 »  All LLMs  »  MBZUAI  »  LLaVA Meta Llama 3 8B Instruct   URL Share it on

  19   

LLaVA Meta Llama 3 8B Instruct is an open-source language model by MBZUAI. Features: 8b LLM, VRAM: 16.7GB, Context: 8K, Instruction-Based, LLM Explorer Score: 0.13.

  Conversational   Endpoints compatible   Instruct   Llava llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MBZUAI/LLaVA-Meta-Llama-3-8B-Instruct 

LLaVA Meta Llama 3 8B Instruct Benchmarks

LLME Score: 0.12841
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaVA Meta Llama 3 8B Instruct (MBZUAI/LLaVA-Meta-Llama-3-8B-Instruct)
🌟 Advertise your project 🚀

LLaVA Meta Llama 3 8B Instruct Parameters and Internals

Model Type 
vision-language
Additional Notes 
Only vision-to-language projector is trained, vision-backbone is frozen.
Training Details 
Data Sources:
LCS-558K, LLaVA-Instruct-665K
Methodology:
Vision-to-Language projector training; LoRA fine-tuning on LLM
Model Architecture:
Merged weights with LLaVA v1.5 and Meta-Llama-3-8B-Instruct
LLM NameLLaVA Meta Llama 3 8B Instruct
Repository 🤗https://huggingface.co/MBZUAI/LLaVA-Meta-Llama-3-8B-Instruct 
Model Size8b
Required VRAM16.7 GB
Updated2026-05-25
MaintainerMBZUAI
Model Typellava_llama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.8 GB: 4-of-4
Model ArchitectureLlavaLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size128257
Torch Data Typefloat16

Best Alternatives to LLaVA Meta Llama 3 8B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Llama3 Llava Next 8B8K / 16.7 GB1524106
Llava Llama 3 8B MultiModal V18K / 16.1 GB31
LLaVA Video Llama 38K / 16.7 GB1394
...VA Meta Llama 3 8B Instruct FT8K / 16.7 GB1612
...Meta Llama 3 8B Instruct FT S28K / 16.7 GB74
LLaVA Llama 3 8B8K / 16.7 GB818
Llava 1.5 Llama 3 8B8K / 16.7 GB90
Vip Llava Llama 3 8B8K / 16.8 GB70
Note: green Score (e.g. "73.2") means that the model is better than MBZUAI/LLaVA-Meta-Llama-3-8B-Instruct.

Rank the LLaVA Meta Llama 3 8B Instruct 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? 53999 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