Get a weekly rundown of the latest AI models and research... subscribe!

Llava V1.6 34b


AI model preview image
The model, llava-v1.6-34b, is a Large Language and Vision Assistant developed by Nous-Hermes. It analyzes a provided image URL and generates a detailed description of the image based on a given prompt. The description can be controlled in terms of length and randomness by adjusting the maximum tokens and temperature respectively. For instance, in the given schema it is providing a detailed analysis of why an image of someone ironing clothes on a moving vehicle is unusual. The description generated by the model is detailed, context-aware, and safety-conscious.

Use cases

LLaVA v1.6-34b is an AI model tailored to generate text analyses of visual content. As its input schema details, this model is capable of interpreting and analyzing images provided in URL format, making it adept at image description and comment generation. This functionality may be utilized to create AI products or practical uses across various disciplines. For instance, software developers could integrate this model into social media platforms to enable auto-captioning for images or to assist visually impaired users in understanding visual content. Similarly, educators can leverage this model to make learning materials more accessible for students with visual impairments. News agencies could also use it to automate the creation of photo captions or to provide descriptive overviews for infographics or complex diagrams. In the realm of surveillance, the model could analyze event footages and generate relevant text descriptions about unusual activities or actions. Operators of e-commerce websites might use this model to generate product descriptors based on images, saving time and effort.



Cost per run
Avg run time

Creator Models

Temporalnet Sdxl$?117
Llava V1.6 Vicuna 13b$?175,659
Jina Embeddings V2 Base En$?38
Jina Embeddings V2 Small En$?32
Llava V1.6 Mistral 7b$?122,847

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Llava V1.6 34b model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameLlava V1.6 34b
LLaVA v1.6: Large Language and Vision Assistant (Nous-Hermes-2-34B)
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-