LLM EXPLORER 59,420 MODELS INDEXED

LLaVA NeXT Video 7B 32K by lmms-lab

By lmms-lab · 250 downloads
HF Repo ↗ Copy URL

LLaVA NeXT Video 7B 32K is an open-source language model by lmms-lab. Features: 7b LLM, VRAM: 15.1GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.12.

  Instruct   Llava mistral   Region:us   Safetensors   Sharded   Tensorflow   Video-text-to-text
Model Card on HF 🤗: https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-7B-32K 

LLaVA NeXT Video 7B 32K Parameters and Internals

Model Type 
Multimodal chatbot, Video-text to text
Use Cases 
Primary Use Cases:
Research on large multimodal models and chatbots
Training Details 
Data Sources:
LAION/CC/SBU, BLIP, GPS-generated, VQA, GPT-4V, ShareGPT, VideoChatGPT-Instruct
Training Time:
April 2024
LLM NameLLaVA NeXT Video 7B 32K
Repository 🤗https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-7B-32K 
Model Size7b
Required VRAM15.1 GB
Updated2026-07-30
Maintainerlmms-lab
Model Typellava_mistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   0.3 GB: 4-of-4   0.0 GB
Model ArchitectureLlavaMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to LLaVA NeXT Video 7B 32K

Best Alternatives
Context / RAM
Downloads
Likes
Llava Med V1.5 Mistral 7B32K / 15.1 GB12304125
Llava V1.6 Mistral 7B32K / 15.1 GB9271246
Llava Mistral 7B Tokenizer32K /  GB92
Candle Llava V1.6 Mistral 7B32K / 15.1 GB11080
Note: green Score (e.g. "73.2") means that the model is better than lmms-lab/LLaVA-NeXT-Video-7B-32K.