OsaurusAI/Qwen-Image-mflux-4bit

Qwen-Image · mflux · 4-bit

Official OsaurusAI 4-bit mflux build of Qwen-Image (Qwen, Apache-2.0), quantized by Osaurus with mflux 0.18. High-quality text-to-image (strong text rendering) for Apple Silicon.

Usage

mflux-generate-qwen --model OsaurusAI/Qwen-Image-mflux-4bit \
  --prompt "a small red cube on a white table" --steps 20

Or load in Osaurus.

Provenance

• Base: Qwen/Qwen-Image © Qwen — Apache-2.0
• Quantization: Osaurus · mflux 0.18 · 4-bit · eric@osaurus.ai