How to run BAGEL-7B-MoT locally

ByteDance Seed · Unified understanding + image gen + edit · 7B params · Apache-2.0 (commercial OK)

ByteDance's open Mixture-of-Transformer-Experts model (7B active, 14B total) that unifies image understanding, SD3-class text-to-image and strong free-form editing, plus emergent abilities like multiview synthesis and world navigation.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 24 GB of VRAM (~29GB total weights (7B active / 14B total MoT); the community INT8 build runs on a single 24GB card, BF16 wants 40GB+.), via Transformers (BAGEL repo).
Rent a GPU — from $0.49/hr. Fits RTX A6000 48GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at ByteDance-Seed/BAGEL-7B-MoT.

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, Image editing, Visual understanding, Free form manipulation, Multiview synthesis
VRAM to run	~24 GB (~29GB total weights (7B active / 14B total MoT); the community INT8 build runs on a single 24GB card, BF16 wants 40GB+.)
Download	~29 GB
Parameters	7B
License	Apache-2.0 (commercial use OK)
Run with	Transformers (BAGEL repo)

Get BAGEL-7B-MoT 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
Emu3.5 — Any to any world model (gen + edit), ~48 GB VRAM
Emu3-Gen — Next token any to any generation, ~18 GB VRAM

Browse: all media models · chat / LLM models