Skip to content

Qwen Image 2512 VRAM requirements

How much VRAM Qwen Image 2512 needs
8-bit: 20.9 GB4-bit GGUF: 12.6 GBAt 1328 × 1328
Type
Image model
Parameters
20.4B
Text encoder
Qwen2.5-VL-7B-Instruct
Released
Dec 2025
License
Apache 2.0

How much VRAM Qwen Image 2512 needs

Memory Qwen Image 2512 needs at each precision
PrecisionWeightsPeak at 1328 × 1328
16-bit BF1638.1 GB39.2 GB
8-bit FP8 · Q8_019.7 GB20.9 GB
6-bit GGUF Q6_K15.7 GB16.8 GB
5-bit GGUF Q5_K_M13.6 GB14.7 GB
4-bit GGUF Q4_K_M · NVFP411.4 GB12.6 GB

The Qwen2.5-VL-7B-Instruct text encoder (7.7 GB at FP8) runs first and then waits in system RAM.

GPUs and Macs that run Qwen Image 2512

How Qwen Image 2512 runs on common GPUs, Macs and AI boxes
MachineBest fitPer imageReport
RTX 4060Too bigPDF: Qwen Image 2512 on RTX 4060 report
RTX 5060Too bigPDF: Qwen Image 2512 on RTX 5060 report
RTX 3070Too bigPDF: Qwen Image 2512 on RTX 3070 report
RTX 3080 10 GBToo bigPDF: Qwen Image 2512 on RTX 3080 10 GB report
RTX 3060 12 GBToo bigPDF: Qwen Image 2512 on RTX 3060 12 GB report
Arc B580Too bigPDF: Qwen Image 2512 on Arc B580 report
RTX 4070Too bigPDF: Qwen Image 2512 on RTX 4070 report
RTX 4070 SuperToo bigPDF: Qwen Image 2512 on RTX 4070 Super report
RTX 5070Too bigPDF: Qwen Image 2512 on RTX 5070 report
RTX 4060 Ti 16 GB5-bit15 minPDF: Qwen Image 2512 on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GB5-bit14 minPDF: Qwen Image 2512 on RTX 5060 Ti 16 GB report
Arc A770 16 GB5-bit12 minPDF: Qwen Image 2512 on Arc A770 16 GB report
Radeon RX 9070 XT5-bit5.8 minPDF: Qwen Image 2512 on Radeon RX 9070 XT report
RTX 4070 Ti Super5-bit7.5 minPDF: Qwen Image 2512 on RTX 4070 Ti Super report
RTX 4080 Super5-bit6.3 minPDF: Qwen Image 2512 on RTX 4080 Super report
RTX 5070 Ti5-bit7.5 minPDF: Qwen Image 2512 on RTX 5070 Ti report
RTX 50805-bit5.9 minPDF: Qwen Image 2512 on RTX 5080 report
Radeon RX 7900 XTX8-bit8.0 minPDF: Qwen Image 2512 on Radeon RX 7900 XTX report
RTX 30908-bit8.1 minPDF: Qwen Image 2512 on RTX 3090 report
RTX 40908-bit3.5 minPDF: Qwen Image 2512 on RTX 4090 report
Radeon AI PRO R97008-bit5.1 minPDF: Qwen Image 2512 on Radeon AI PRO R9700 report
RTX 50908-bit2.7 minPDF: Qwen Image 2512 on RTX 5090 report
RTX PRO 5000 Blackwell 48 GB16-bit2.2 minPDF: Qwen Image 2512 on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada16-bit1.6 minPDF: Qwen Image 2512 on RTX 6000 Ada report
L40S16-bit1.6 minPDF: Qwen Image 2512 on L40S report
RTX PRO 6000 Blackwell16-bit70 sPDF: Qwen Image 2512 on RTX PRO 6000 Blackwell report
Mac mini M4 16 GBToo bigPDF: Qwen Image 2512 on Mac mini M4 16 GB report
Mac mini M4 24 GBToo bigPDF: Qwen Image 2512 on Mac mini M4 24 GB report
Mac mini M4 32 GBToo bigPDF: Qwen Image 2512 on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GBToo bigPDF: Qwen Image 2512 on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit75 minPDF: Qwen Image 2512 on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit75 minPDF: Qwen Image 2512 on Mac mini M4 Pro 64 GB report
M4 Max 128 GB16-bit37 minPDF: Qwen Image 2512 on M4 Max 128 GB report
M5 Max 128 GB16-bit11 minPDF: Qwen Image 2512 on M5 Max 128 GB report
M3 Ultra 96 GB16-bit21 minPDF: Qwen Image 2512 on M3 Ultra 96 GB report
M3 Ultra 256 GB16-bit21 minPDF: Qwen Image 2512 on M3 Ultra 256 GB report
M3 Ultra 512 GB16-bit21 minPDF: Qwen Image 2512 on M3 Ultra 512 GB report
M5 Ultra 512 GB16-bit6.6 minPDF: Qwen Image 2512 on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit17 minPDF: Qwen Image 2512 on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB16-bit17 minPDF: Qwen Image 2512 on Ryzen AI Max+ 395 128 GB report
RTX Spark16-bit9.2 minPDF: Qwen Image 2512 on RTX Spark report
DGX Spark16-bit9.2 minPDF: Qwen Image 2512 on DGX Spark report
DGX Station GB30016-bit15 sPDF: Qwen Image 2512 on DGX Station GB300 report
A100 80 GB SXM16-bit1.8 minPDF: Qwen Image 2512 on A100 80 GB SXM report
H100 SXM16-bit36 sPDF: Qwen Image 2512 on H100 SXM report

1328 × 1328, 50 steps. Times are rough, plus or minus 30%.

Where to get it

Questions

How much VRAM does Qwen Image 2512 need?

Qwen Image 2512 needs about 20.9 GB at 8-bit, or 12.6 GB as a 4-bit GGUF, at its default output size.

What is the minimum VRAM for Qwen Image 2512?

The minimum is about 12.6 GB of VRAM, as a 4-bit file at its default output size, with the text encoder parked in system RAM.

How big is Qwen Image 2512?

The 20.4B denoiser is 38.1 GB at 16-bit and 19.7 GB at 8-bit; the Qwen2.5-VL-7B-Instruct text encoder comes on top.

Can Qwen Image 2512 run on an RTX 4090?

Yes. At 8-bit it takes about 3.5 min per image.

More models