SDXL-Lightning (4-step) on BeagleBone AI-64 (4 GB)

Can the BeagleBone AI-64 (4 GB) run SDXL-Lightning (4-step)?

No, it doesn’t fit

No. SDXL-Lightning (4-step) needs about 2.9 GB even at FP8; the BeagleBone AI-64 (4 GB) has 2.8 GB usable.

Download SDXL-Lightning (4-step)

Original weights · Hugging Face

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

huggingface.co/ByteDance/SDXL-Lightning (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP8, 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 Won't run: How well it runs on the BeagleBone AI-64 (4 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.	7.1 / 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.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	7.1 / 100

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

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every precision on the BeagleBone AI-64 (4 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	3.8 GB	2.8 GB	—	—	Won't run	54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	2.9 GB	2.8 GB	—	—	Won't run	52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Hardware that can run it

54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 FP16 · 2.9 s · Runs great
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB FP16 · 2.9 s · Runs great
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER FP16 · 1.3 s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 FP8 · 2.3 s · Runs great
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP16 · 0.9 s · Runs great
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB FP16 · 1.9 s · Runs great

Models that do run on the BeagleBone AI-64 (4 GB)

28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. SD Turbo FP16 · 30 s
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. Realistic Vision V5.1 FP16 · 7.6 min
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. DreamShaper 8 FP16 · 7.6 min
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. LCM DreamShaper v7 FP16 · 1.6 min
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. PixArt-Σ XL 1024 FP16 · 11.8 min

Quick answers

How much memory does SDXL-Lightning (4-step) need on the BeagleBone AI-64 4GB?

Even at FP8 it needs about 2.9 GB; the BeagleBone AI-64 4GB has 2.8 GB usable.

What can the BeagleBone AI-64 4GB run instead?

SD Turbo, Realistic Vision V5.1 and DreamShaper 8 run best on it; the page lists more, each with its speed.

What hardware can run SDXL-Lightning (4-step)?

Arc B580 12GB, RTX 3060 12GB and RTX 4070 SUPER 12GB run it; the page lists more, each with its 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.