Comfy-Org/Qwen-Image-2.1
Comfy-Org/Qwen-Image-2.1
Parameters
7.1B
Context
—
Downloads
9.9M
Likes
1.3K
Architecture
—
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 29.5 GB RAM 44.3 · Disk 59.7 | 32.0 GB RAM 48.1 · Disk 85.7 | 35.8 GB RAM 53.7 · Disk 124.7 |
| FP88bit | 16.4 GB RAM 32.0 · Disk 49.3 | 18.3 GB RAM 32.0 · Disk 75.3 | 21.5 GB RAM 32.3 · Disk 114.3 |
| INT88bit | 16.4 GB RAM 32.0 · Disk 49.3 | 18.3 GB RAM 32.0 · Disk 75.3 | 21.5 GB RAM 32.3 · Disk 114.3 |
| AWQ4bit | 10.1 GB RAM 32.0 · Disk 44.4 | 11.7 GB RAM 32.0 · Disk 70.4 | 14.6 GB RAM 32.0 · Disk 109.4 |
| GPTQ4bit | 10.2 GB RAM 32.0 · Disk 44.4 | 11.8 GB RAM 32.0 · Disk 70.4 | 14.7 GB RAM 32.0 · Disk 109.4 |
| GGUF4bit | 10.4 GB RAM 32.0 · Disk 44.6 | 12.0 GB RAM 32.0 · Disk 70.6 | 14.9 GB RAM 32.0 · Disk 109.6 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 33.9 img/min
Effective production throughput ≈ 23.7 images/min
score 0.6893
1× Tesla V100
16 GB VRAM
≈ 0 img/min (N/A — benchmark unavailable)
Effective production throughput ≈ 0 images/min
score 0.6846
8× RTX 5090
256 GB VRAM
≈ 501.6 img/min
Effective production throughput ≈ 351.1 images/min
score 0.3522
1× L4
24 GB VRAM
≈ 36.3 img/min
Effective production throughput ≈ 25.4 images/min
score 0.6208
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$35.7
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.5
/mo · vast
L4
24 GB VRAM
$76.2
/mo · vast
RTX 3080 Ti
12 GB VRAM
$78.8
/mo · vast
RTX 3090
24 GB VRAM
$79.6
/mo · vast