Can My GPU Run RealVisXL v5.0?

Text to Image · VRAM requirements and compatibility for 78 GPUs

Home › AI Models › RealVisXL v5.0

Photorealistic image generation, great for portraits. RealVisXL v5.0 is a text to image model — developed by SG161222, released 2024-04, 3.5B parameters, 6.9 GB download, license: openrail++.

Short answer: you need at least 4 GB of VRAM (8 GB recommended). 78 of 78 GPUs can run it; the smallest NVIDIA card that can is the GTX 1060 6GB (6 GB).

Check RealVisXL v5.0 on your GPU

RealVisXL v5.0 VRAM requirements

FormatVRAM
FP16 (full precision)7 GB
FP85 GB
Minimum4 GB
Recommended8 GB
Optimal12 GB

Tip: Photorealistic SDXL model. Great for portraits.

Available as: ComfyUI, Diffusers, FP8 versions, CPU offloading.

Official pages: Civitai

Which GPUs can run RealVisXL v5.0?

Ratings go from S (perfect) to F (can't run) and use the best format that fits in each card's VRAM. How ratings work.

NVIDIA

GPUVRAMRatingRuns asSpeed
RTX 509032 GBS PerfectFP16FastDetails
RTX 508016 GBA GreatFP16FastDetails
RTX 5070 Ti16 GBA GreatFP16FastDetails
RTX 507012 GBA GreatFP16FastDetails
RTX 5060 Ti 16GB16 GBB GoodFP16FastDetails
RTX 5060 Ti 8GB8 GBB GoodFP16ModerateDetails
RTX 50608 GBB GoodFP16ModerateDetails
RTX 409024 GBS PerfectFP16FastDetails
RTX 4080 Super16 GBA GreatFP16FastDetails
RTX 408016 GBA GreatFP16FastDetails
RTX 4070 Ti Super16 GBA GreatFP16FastDetails
RTX 4070 Ti12 GBA GreatFP16FastDetails
RTX 4070 Super12 GBA GreatFP16FastDetails
RTX 407012 GBB GoodFP16FastDetails
RTX 4060 Ti 16GB16 GBB GoodFP16FastDetails
RTX 4060 Ti 8GB8 GBB GoodFP16ModerateDetails
RTX 40608 GBC UsableFP16ModerateDetails
RTX 3090 Ti24 GBA GreatFP16FastDetails
RTX 309024 GBA GreatFP16FastDetails
RTX 3080 Ti12 GBA GreatFP16FastDetails
RTX 3080 12GB12 GBA GreatFP16FastDetails
RTX 3080 10GB10 GBB GoodFP16FastDetails
RTX 3070 Ti8 GBB GoodFP16ModerateDetails
RTX 30708 GBB GoodFP16ModerateDetails
RTX 3060 Ti8 GBB GoodFP16ModerateDetails
RTX 50508 GBC UsableFP16ModerateDetails
RTX 306012 GBB GoodFP16ModerateDetails
RTX 2080 Ti11 GBB GoodFP16ModerateDetails
RTX 2080 Super8 GBC UsableFP16ModerateDetails
RTX 20808 GBC UsableFP16ModerateDetails
RTX 2070 Super8 GBC UsableFP16ModerateDetails
RTX 20708 GBC UsableFP16ModerateDetails
RTX 2060 Super8 GBC UsableFP16ModerateDetails
RTX 20606 GBC UsableOffloadVery SlowDetails
GTX 1080 Ti11 GBB GoodFP16ModerateDetails
GTX 10808 GBC UsableFP16ModerateDetails
GTX 1070 Ti8 GBC UsableFP16ModerateDetails
GTX 10708 GBC UsableFP16ModerateDetails
GTX 1060 6GB6 GBC UsableOffloadVery SlowDetails

AMD

GPUVRAMRatingRuns asSpeed
RX 9070 XT16 GBA GreatFP16FastDetails
RX 907016 GBA GreatFP16FastDetails
RX 7900 XTX24 GBA GreatFP16FastDetails
RX 9070 GRE12 GBB GoodFP16FastDetails
RX 7900 XT20 GBA GreatFP16FastDetails
RX 9060 XT 16GB16 GBB GoodFP16FastDetails
RX 9060 XT 8GB8 GBB GoodFP16ModerateDetails
RX 7900 GRE16 GBB GoodFP16FastDetails
RX 7800 XT16 GBB GoodFP16FastDetails
RX 7700 XT12 GBB GoodFP16ModerateDetails
RX 7600 XT16 GBB GoodFP16ModerateDetails
RX 76008 GBC UsableFP16ModerateDetails
RX 6950 XT16 GBB GoodFP16ModerateDetails
RX 6900 XT16 GBB GoodFP16ModerateDetails
RX 6800 XT16 GBB GoodFP16ModerateDetails
RX 680016 GBB GoodFP16ModerateDetails
RX 6700 XT12 GBB GoodFP16ModerateDetails
RX 6600 XT8 GBC UsableFP16SlowDetails
RX 66008 GBC UsableFP16SlowDetails

Apple

GPUVRAMRatingRuns asSpeed
M5 Ultra96 GBA GreatFP16FastDetails
M3 Ultra96 GBB GoodFP16FastDetails
M4 Max48 GBB GoodFP16FastDetails
M5 Max48 GBB GoodFP16FastDetails
M4 Pro24 GBB GoodFP16ModerateDetails
M5 Pro24 GBB GoodFP16ModerateDetails
M416 GBC UsableFP16ModerateDetails
M3 Max36 GBB GoodFP16FastDetails
M3 Pro18 GBC UsableFP16ModerateDetails
M516 GBC UsableFP16ModerateDetails
M616 GBC UsableFP16ModerateDetails
M316 GBC UsableFP16ModerateDetails
M2 Ultra192 GBB GoodFP16FastDetails
M2 Max96 GBB GoodFP16FastDetails
M2 Pro32 GBC UsableFP16ModerateDetails
M224 GBC UsableFP16ModerateDetails
M1 Ultra128 GBB GoodFP16FastDetails
M1 Max64 GBB GoodFP16FastDetails
M1 Pro32 GBC UsableFP16ModerateDetails
M116 GBC UsableFP16SlowDetails

Frequently asked questions

How much VRAM does RealVisXL v5.0 need?

RealVisXL v5.0 needs at least 4 GB of VRAM, 8 GB recommended, and 7 GB to run at full FP16 precision.

Can RealVisXL v5.0 run on 8 GB of VRAM (e.g. NVIDIA RTX 4060)?

On the NVIDIA RTX 4060: yes, in FP16 (rating C, usable).

Can RealVisXL v5.0 run on the NVIDIA RTX 3060 (12 GB)?

Yes, in FP16 (rating B, good).

Which GPUs can run RealVisXL v5.0?

78 of the 78 GPUs we track can run it, and 54 run it well (rating B or better). The cheapest one that runs it well is the NVIDIA RTX 5060 (8 GB, about $299).

Does RealVisXL v5.0 work on AMD or Apple Silicon?

19 AMD Radeon and 20 Apple Silicon chips in our list can run it.

Similar text to image models