Can RTX 4090 run Stable Diffusion XL (CoreML)?

Yes — runs locally

~144 tok/sec · Instant — feels like typing. No noticeable delay.

Your VRAM

24 GB

Model size

3.5B

Best quant

CoreML

VRAM needed

3.3 GB

The verdict

The RTX 4090 (24 GB VRAM) handles Stable Diffusion XL (CoreML) comfortably using the CoreML quantization, which fits in 3.3 GB. Expected throughput is around 144 tokens/second, which feels Instant — feels like typing. No noticeable delay. in interactive use. Higher quality image generation. CoreML optimized for iOS. Requires 6GB+ usable memory (iPad/Mac recommended).

Setup tutorial: Stable Diffusion XL (CoreML) on RTX 4090

AI-generated, GPU-specific. Verified commands for your exact hardware.

TL;DR

Stable Diffusion XL (CoreML) runs at Grade S on an NVIDIA GeForce RTX 4090 with ~347 tok/sec using the CoreML quantization (2.8GB file, 3.3GB VRAM).

Prerequisites

Before starting, ensure you have at least 10GB of free disk space, a 64-bit version of Windows or Linux, the latest NVIDIA drivers (version 525.60.11 or later), and CUDA 11.8 installed.

Expected performance

You can expect ~347 tok/sec with 3.3GB VRAM in use, leaving 20.7GB of VRAM headroom for larger context windows. Given the remaining VRAM, you can achieve a practical context window of several thousand tokens.

1. Install runtimeOllama

pip install ollama
ollama init

2. Download the model

Download the CoreML quantized version of Stable Diffusion XL (2.8GB file) from Hugging Face.

ollama pull apple/coreml-stable-diffusion-xl-base-ios

3. Run it

ollama run --model apple/coreml-stable-diffusion-xl-base-ios --device cuda
ollama interactive

4. Optimize for RTX 4090

For optimal performance on the NVIDIA GeForce RTX 4090 with 24GB VRAM, set --n-gpu-layers to 32 to fully utilize the GPU. Enable flash attention (--flash-attn) to speed up inference. With 20.7GB of VRAM headroom, you can handle larger context windows without running out of memory.

Troubleshooting

Out of memory errors during inference

Reduce the number of layers on the GPU using --n-gpu-layers <num_layers> or decrease the batch size.

Slow inference times

Ensure CUDA is properly installed and enabled with --device cuda. Also, enable flash attention with --flash-attn.

Model not loading

Check if the model file is corrupted or incomplete. Re-download the model using the 'ollama pull' command.

Alternative runtimes

Alternative runtimes include LM Studio and llama.cpp. Use LM Studio for a more user-friendly interface and llama.cpp for lightweight, standalone execution. Jan is another option for distributed training and inference, but Ollama provides a balanced approach for both development and production on the NVIDIA GeForce RTX 4090.

Full Stable Diffusion XL (CoreML) details →

Other models that run great on RTX 4090

FAQ (20)

What GPU do I need to run Stable Diffusion XL (CoreML)?

Stable Diffusion XL (CoreML) is optimized for iOS devices and does not require a specific GPU. It leverages the Metal Performance Shaders (MPS) framework on iPad and Mac.

Is Stable Diffusion XL (CoreML) good for coding?

Stable Diffusion XL (CoreML) is primarily designed for generating high-quality images and is not optimized for coding tasks.

Stable Diffusion XL (CoreML) vs Llama 3.1 8B?

Stable Diffusion XL (CoreML) is an image generation model with 3.5B parameters, while Llama 3.1 8B is a text generation model with 8B parameters. They serve different purposes and are not directly comparable.

Can I run Stable Diffusion XL (CoreML) on a Mac?

Yes, Stable Diffusion XL (CoreML) can run on a Mac, but it requires at least 6GB of usable memory and is optimized for iOS devices like iPads.

How much VRAM does Stable Diffusion XL (CoreML) need?

Stable Diffusion XL (CoreML) requires 3.3 GB of VRAM, which is consistent across different quantization levels.

Is Stable Diffusion XL (CoreML) censored?

The model is not inherently censored, but it adheres to the CreativeML OpenRail-M license, which may have usage guidelines and restrictions.

Is Stable Diffusion XL (CoreML) commercial-use allowed?

Yes, Stable Diffusion XL (CoreML) can be used commercially, but you must comply with the terms of the CreativeML OpenRail-M license.

Stable Diffusion XL (CoreML) context length?

The context length for Stable Diffusion XL (CoreML) is not specified, as it is primarily an image generation model and does not handle text input in the same way as language models.

Want personalized recommendations for your exact setup? Detect my hardware →