SDXL Turbo on NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Can the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB) run SDXL Turbo?

Yes, it runs great

Runs great. At FP16 it needs about 7.6 GB of 16.0 GB usable and takes about 0.4 s per image.

Best precision: FP16
Memory mode: Everything on GPU
Time per image: 0.4 s
Output: 512×512, 1 steps

Best app to run it on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

On Linux

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download SDXL Turbo

Original weights · Hugging Face

Full-precision files from Stability AI, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/stabilityai/sdxl-turbo (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Stability AI. The weights themselves download from Hugging Face.

github.com/Stability-AI/generative-models (opens in a new tab)

git clone https://github.com/Stability-AI/generative-models

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP16, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	18.0 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	11.0 / 15
Match score	69.0 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	7.6 GB	16.0 GB	0.4 s	Everything on GPU	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	4.2 GB	16.0 GB	0.3 s	Everything on GPU	Runs great	39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 (16 GB) FP16 · 3.8 s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 (16 GB) FP16 · 2.6 s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 FP16 · 0.6 s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB FP16 · 0.6 s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER FP16 · 0.3 s · Runs great
39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 FP8 · 0.5 s · Runs great

Quick answers

How much memory does SDXL Turbo need on the NVIDIA RTX Spark N1X (5120-core GPU) 32GB?

At FP16 it needs about 7.6 GB. The NVIDIA RTX Spark N1X (5120-core GPU) 32GB has 16.0 GB usable.

How long does SDXL Turbo take on the NVIDIA RTX Spark N1X (5120-core GPU) 32GB?

About 0.4 s per image at FP16 and default settings, an estimate scaled from a reference timing by this hardware’s compute speed.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.