Qwen-Image-2512-Lightning
This model suite supports two mainstream usage frameworks, with detailed guides provided below:
Params
20.4 B
Context
—
Downloads 30d
95 K
Likes
231
Download history
daily snapshots · 106 days
▲ 92 K in the last 30 days (49.2%)
181 K91 K
Oct 12Oct 22Nov 1Nov 10
214 K64 K
Aug 13Sep 12Oct 12Nov 10
214 K64 K
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | fp16 | 107.5 GB | 121.8 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 20.4 B
- Licence
- apache-2.0
- First seen on the Hub
- 2025-12-31
- Base model
- Qwen-Image-2512
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-to-image model
Popular comparisons
Appears in