AxForge
Sign in Get started

Model reference · open weights

llava-vicuna

LLMs llava-hf Vision + text 1 build Open, with conditions 26k dl/mo

llava-vicuna is an open-weight language model from llava-hf. llava-v1.6-vicuna-7b-hf (FP16) weighs 14.1 GB; the smallest configuration that runs it is RTX 4090 24 GB.

Request Rent a GPU

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • llava-vicuna is a 7.1B parameter multimodal model designed for image-text-to-text tasks such as image captioning and visual question answering.
  • It supports a context length of 4096 tokens and operates in English under the llama2 licence.

Summary of the llava-hf/llava-v1.6-vicuna-7b-hf model card, 2026-10-01

Hugging Face ↗Paper ↗

What it is

Released byllava-hf
Released2024-03-17
Parameters7.1B
VRAM14.1 GB for the weights

What it runs on

Memory and cards for llava-v1.6-vicuna-7b-hf (FP16)

14.1 GBweights, file size
2.0 GBruntime overhead, at least
4,096 tokenscontext max

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

CardWeights alone
RTX 3060 12 GB … RTX 4060 Ti 16 GB
2 smaller cards		does not fit
RTX 3090 24 GBfits
RTX 4090 24 GBfits
RTX 5090 32 GBfits
L40S 48 GBfits
A100 80 GBfits
H100 80 GBfits
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms