Qwen-Image-2.1-Turbo-FP8
This is an FP8 / INT8 quantized version of Qwen-Image-2.1-Turbo, the 8-step distilled checkpoint of Qwen-Image-2.1. - Each file replaces the 14.2 GB bf16 transformer with a 7.1 to 7.3 GB one. - Same-seed LPIPS vs the bf16 Turbo model (lower is better): 0.037 INT8-ConvRot, 0.089 INT8, 0.125 FP8. INT8-ConvRot is the recommended file. - Turbo shares its text encoder and VAE with Qwen-Image-2.1 (text encoder byte-identic...
Params
7.1 B
Context
—
Downloads 30d
192 K
Likes
24
Download history
daily snapshots · 10 days192 K66 K
Oct 15Oct 18Oct 21Oct 24
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 | bf16 | 54.1 GB | 61.1 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
- 7.1 B
- Tensor type
- BF16
- Licence
- other
- First seen on the Hub
- 2026-10-10
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-15
Compare with any text-to-image model