Qwen-Image-2.1-Turbo-Quantized vs Krea2_FP8
Specs, VRAM requirements and download trends — updated 4 November 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen-Image-2.1-Turbo-Quantized | Krea2_FP8 |
|---|---|---|
| Parameters | — | — |
| Architecture | — | — |
| Context length | — | — |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | — | — |
| Downloads 30d | 89,977 | 97,380 |
| Downloads all time | 2.1 M | 378 K |
| Quantizations on the Hub | GGUF, SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-09-20 | 2026-06-22 |
Download trend
Daily snapshots, last 7 days (4 Nov – 10 Nov)
2.5 M49 K
Qwen-Image-2.1-Turbo-Quantized
Krea2_FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen-Image-2.1-Turbo-Quantized · Q4_0
5.0 GB / 24 GB
Krea2_FP8 · fp16
20.7 GB / 24 GB
Qwen-Image-2.1-Turbo-Quantized · fp16
70.3 GB / 24 GB