Models🧠
Qwen2.5 0.5B
Released Sep 19, 2024Qwen3.8-Max
Ultra-compact 0.5B-parameter model. Runs on any hardware, even embedded: ideal for lightweight summarization and low-power local devices.
LLMQwenLeggeroOpen Source
Back to resources
Qwen-Image 2.1
Released on Sep 20, 2026
7B open-weight model (32-layer DiT) that unifies text-to-image generation up to 2048x2048, editing with up to 10 reference images, and native RGBA transparency. Designed to run locally on 16GB+ VRAM; supported by diffusers and ComfyUI.
Features
- 7B parameters (32-layer DiT)
- Generation + editing + RGBA transparency
- Up to 10 reference images
- Output up to 2048x2048
- Runs locally (diffusers, ComfyUI)
Version history
- 2.1Latest
Generazione e editing unificati in 7B, trasparenza RGBA nativa, fino a 10 immagini di riferimento, output 2048x2048.
Tags
Useful links
Discover Qwen-Image 2.1
Visit the official site to download, learn more and start using Qwen-Image 2.1.
Related resources — Models
Models🧠
Qwen2.5 14B
Released Sep 19, 2024Qwen3.8-Max
Clear step up in reasoning and instruction quality over 8B models. Excellent for coding, agents and structured writing on 16GB GPUs or Macs with 32GB RAM.
LLMQwenCodingOpen Source
Models🧠
Qwen2.5 32B
Released Sep 19, 2024Qwen3.8-Max
Near-70B quality at a fraction of the size: the sweet spot for advanced use. Excellent in Italian, code and reasoning. Needs 24GB+ VRAM.
LLMQwenAvanzatoOpen Source