RUN THIS LLM

Search local LLM hardware requirements

← Back to all models

BAGEL 14B MoT

ByteDance · 14B MoT · Image Gen

ByteDance's unified understanding-and-generation model: a Mixture-of-Transformers with 14B total / 7B active params built from Qwen2.5-7B, SigLIP, and the FLUX VAE. Does text-to-image, free-form editing, and VLM-style understanding in one model; Apache 2.0.

VRAM Requirements

QuantizationVRAM
FP16 (full quality)14 GB

Specifications

Benchmarks

Loading interactive analysis...

RTL
Add Run This LLM to your home screen
Get the Chrome Extension
Look up hardware requirements for any model right from your browser sidebar — no tab switching needed.
Add to Chrome — It's Free