How to run Janus-Pro-1B locally

DeepSeek · Unified understanding + image gen · 1.5B params · DeepSeek Model License (code MIT) (commercial OK)

The 1.5B-class little sibling of Janus-Pro that still does both image understanding and text-to-image generation, aimed at low-VRAM and edge use. Weights under the commercial-friendly DeepSeek Model License.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 6.0 GB of VRAM (~4GB in BF16; comfortably runs on a 6-8GB consumer GPU or even CPU, the most accessible unified gen+understanding model on the list.), via Transformers (Janus repo).
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at deepseek-ai/Janus-Pro-1B.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → image, Visual understanding, Image captioning, Visual question answering
VRAM to run	~6.0 GB (~4GB in BF16; comfortably runs on a 6-8GB consumer GPU or even CPU, the most accessible unified gen+understanding model on the list.)
Download	~4 GB
Parameters	1.5B
License	DeepSeek Model License (code MIT) (commercial use OK)
Run with	Transformers (Janus repo)

Get Janus-Pro-1B on Hugging Face →

More multimodal / omni models

Qwen2.5-Omni-7B — Omni understanding + speech generation, ~24 GB VRAM
Janus-Pro-7B — Unified understanding + image gen, ~16 GB VRAM
OmniGen2 — Any to image (gen + edit + in context), ~17 GB VRAM
MiniCPM-o 2.6 — Omni understanding + speech generation, ~9.0 GB VRAM
BAGEL-7B-MoT — Unified understanding + image gen + edit, ~24 GB VRAM
Emu3.5 — Any to any world model (gen + edit), ~48 GB VRAM

Browse: all media models · chat / LLM models