RealVisXL_V4.0
SG161222openrail++textvision

RealVisXL_V4.0

Updated Nov 21, 2026
Parameters
2.6B
License
openrail++
Updated
Nov 21, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit RealVisXL_V4.0 with real runtime overhead.
Q4_K_M
2 GB
Q5_K_M
2 GB
Q8_0
3 GB
FP16
5 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve SG161222/RealVisXL_V4.0

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

RealVisXL_V4.0 is an open-weight image generation model published by SG161222 on Hugging Face in February 2024, with 2.6B parameters under the openrail++ license.

Among the 26 image generation models in this directory it ranks 19th by monthly Hugging Face downloads, and 13 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 5 GB; 8-bit brings that to ~3 GB and 4-bit (Q4_K_M) to ~2 GB, before activations and any context or image buffers. A 12 GB consumer card holds it at 4-bit; FP16 needs a 24 GB card such as an RTX 4090. Check exact numbers for your card with the VRAM calculator.

Similar image generation modelsLink to this section

PopularityLink to this section

RealVisXL_V4.0 was downloaded 197,691 times on Hugging Face in the last month (7,353,845 all-time) and has 301 likes.

Run it locallyLink to this section

Weights and usage instructions are on the SG161222/RealVisXL_V4.0 model card; it loads with Hugging Face Diffusers (or ComfyUI).

Local runtimes that fit this model:

  • comfyui - node-based workflows, the usual way to run diffusion models locally
  • invokeai - a canvas UI for image generation and editing

From the community

What users are saying

“Hi! Thank you so much! I think RealVis on SD 3.0 base is my next goal (if I can train the model locally).”

“![image.png](https://cdn-uploads.huggingface.co/production/uploads/636da884c4a7a729c162a94e/0-f8g9egaq-sNrXiteoDb.png)”

Frequently asked

Quick answers to common questions

How much VRAM does RealVisXL_V4.0 need?

RealVisXL_V4.0 with 2.6B parameters needs approximately 2 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is RealVisXL_V4.0 better than other SG161222 models?

RealVisXL_V4.0 has 2.6B parameters - a strong choice for image-generation.

What license is RealVisXL_V4.0 under?

RealVisXL_V4.0 is released under the openrail++ license, making it suitable for most commercial and personal projects.

What hardware runs RealVisXL_V4.0 well?

With 2.6B parameters, RealVisXL_V4.0 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for RealVisXL_V4.0?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~2 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with RealVisXL_V4.0?

RealVisXL_V4.0 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec