Benchmark search

Try these searches

Found 18 run configurations

Each row is a run configuration (model + hardware + framework + quantization); repeated runs of the same setup are merged — raw counts appear in each result’s source line.

ModelQwen-Image-2.1

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 3090 · 24GB · Diffusers

Other

2026-10-06

14.2 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Diffusers 0.32.0 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 3090 · 24GB · Diffusers

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Diffusers 0.32.0 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 3090 · 24GB · Nunchaku

Other

2026-10-06

14.2 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Nunchaku 0.3.2 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 3090 · 24GB · Nunchaku

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Nunchaku 0.3.2 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 5070 Ti · 16GB · Diffusers

Other

2026-10-06

53.3 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Diffusers 0.32.0 1920x1080

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 5070 Ti · 16GB · Diffusers

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Diffusers 0.32.0 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 5070 Ti · 16GB · Nunchaku

Other

2026-10-06

14.2 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Nunchaku 0.3.2 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 5070 Ti · 16GB · Nunchaku

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Nunchaku 0.3.2 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 5090 · 32GB · Diffusers

Other

2026-10-06

14.2 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Diffusers 0.32.0 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 5090 · 32GB · Diffusers

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Diffusers 0.32.0 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 5090 · 32GB · Nunchaku

Other

2026-10-06

53.3 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Nunchaku 0.3.2 1920x1080

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 5090 · 32GB · Nunchaku

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Nunchaku 0.3.2 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 4090 · 24GB · Diffusers

Other

2026-10-06

14.2 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Diffusers 0.32.0 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 4090 · 24GB · Diffusers

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Diffusers 0.32.0 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · FP8

L0 Self-reported

NVIDIA RTX 4090 · 24GB · Nunchaku

Other

2026-10-06

14.2 s

Gen time

8.2 GB

VRAM

Config (latest run)
Linux CUDA 12.6 FP8 Nunchaku 0.3.2 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NF4

L0 Self-reported

NVIDIA RTX 4090 · 24GB · Nunchaku

Other

2026-10-06

7.1 s

Gen time

4.3 GB

VRAM

Config (latest run)
Linux CUDA 12.6 NF4 Nunchaku 0.3.2 1024x1024

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · NVFP4 rank-128

L0 Self-reported

NVIDIA RTX 5090 · 32GB · Nunchaku

Other

2026-09-27

4.76 s

Gen time

18.74 GB

VRAM

Config (latest run)
未知 NVFP4 rank-128 Nunchaku custom runtime (2026-09) 1024x1024 · 25 steps

Sources: Other · 1 runs · 1 independent sources

Qwen-Image-2.1 · INT8 ConvRot

L0 Self-reported

NVIDIA RTX 5060 Ti 16GB · 16GB · ComfyUI

GitHub

2026-09-27

18.5 s

Gen time

15.44 GB

VRAM

Config (latest run)
Windows CUDA 13.0 INT8 ConvRot ComfyUI 0.37.0 1024x1024 · 25 steps

Sources: GitHub · 1 runs · 1 independent sources

18 results

Related models
Related hardware
Related frameworks
Related quantizations