Nexa AI On-Device Model Hub | Explore Gemma, LLaMa, Qwen, Stable Diffusion, Whisper & Leading On-Device AI Models and Run Models Locally On Your Device

New to quantized models and on-device AI? Learn basics and how to select in Nexa Docs

Task

Text

Chat

Code

Math

Long Context

Translation

Vision

Image Generation

Video Generation

Audio

Speech-recognition

Speech Generation (TTS)

Audio Generation

Multimodal

Vision+Text in

Audio+Text

Other

Uncensored

Tool-use

Text Embedding

Parameters

B

to

B

/

126 models

liuhaotian/

llava-v1.6-vicuna-7b

Updated on 08/22/2024

NexaAI/

omnivision

Updated 6 days ago

google/

gemma-1.1-2b-instruct

Updated on 08/21/2024

meta/

Llama3.2-3B-Instruct

Updated on 09/25/2024

BlackForestLabs/

FLUX.1-schnell

Image Generation

Updated on 09/10/2024

Systran/

faster-whisper-tiny

Speech-recognition

Updated on 08/21/2024

runwayml/

stable-diffusion-v1-4

Image Generation

Updated on 08/22/2024

suno/

bark-small

Speech Generation (TTS)

Updated on 10/22/2024

Qwen/

Qwen2-Audio-7.8B-Instruct

Updated on 11/14/2024

Systran/

faster-whisper-large-v3-turbo

Speech-recognition

Updated on 10/01/2024

meta/

Llama3.2-1B-Instruct

Updated on 10/26/2024

SimianLuo/

lcm-dreamshaper-v7

Image Generation

Updated on 08/22/2024

qnguyen3/

nanoLLaVA

Updated on 11/07/2024

google/

gemma-2-2b-instruct

Updated on 08/21/2024

Orenguteng/

Llama3-8B-Lexi-Uncensored

Updated on 08/22/2024

NexaAI/

Octopus-v2

Updated on 09/10/2024

NexaAI/

omniaudio

Updated on 11/11/2024

nomic-ai/

nomic-embed-text-v1.5

Updated on 10/10/2024

meta/

Llama3.1-8B-Instruct

Updated on 08/22/2024

xtuner/

llava-llama-3-8b-v1.1

Updated on 08/22/2024