Qwen-Image-2.1 · INT8 ConvRot
This page aggregates 1 real-world runs of Qwen-Image-2.1 (INT8 ConvRot) on NVIDIA RTX 5060 Ti 16GB with ComfyUI, contributed by 1 independent source platforms; metrics are averages of published measurements.
18.5 s
Gen time
Per image / per clip
15.44 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
GitHub
Source platforms
6 days ago
Last verified
Performance
No published records for this metric under the same model + hardware yet
Core figures
- Gen time (avg)
- 18.5 s
- VRAM (avg)
- 15.44 GB
- Power draw
- — W
- Output
- 1024x1024 · 25 steps
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen-Image-2.1
- Quantization
- INT8 ConvRot
- Framework
- ComfyUI
- Version
- 0.37.0
- Batch size
- 1
- Output spec
- 1024x1024 · 25 steps
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5060 Ti 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 15.44 GB
- OS
- Windows
- CUDA
- 13.0
Get started
Weights for this deployment
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Startup command
Command from the latest benchmark runpython_embeded/python.exe ComfyUI/main.py --port 8199Sources & evidence
1 measured records in total, each traceable to its original source
0.37.0 · Windows · CUDA 13.0
18.5 s
Gen time
15.44 GB
VRAM
— W
Power draw
RTX5060Ti16GB，ComfyUI0.37.0、torch2.13.0+cu130；DiT和文本编码器INT8 ConvRot，BF16 VAE。1024²、25步，warm整次18.5s，sampling15.9s；采样峰值15806MiB≈15.44GiB，接近容量上限。