Stable Cascade on Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)
Can the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB) run Stable Cascade?
Barely: it runs very slowly
Very slow. At FP16 it needs about 14.0 GB of 230 GB usable, with an estimated speed of 4.1 min.
- Best precision
FP16- Memory mode
- Everything on GPU
- Time per image
- 4.1 min
- Output
- 1024×1024, 30 steps
Download Stable Cascade
Original weights · Hugging Face
Full-precision files from Stability AI, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.
huggingface.co/stabilityai/stable-cascade (opens in a new tab)
Official repo · GitHub
Reference code, inference scripts and docs from Stability AI. The weights themselves download from Hugging Face.
github.com/Stability-AI/StableCascade (opens in a new tab)
git clone https://github.com/Stability-AI/StableCascadeHow it’s rated
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 quality | 23.4 / 45 | |
|---|---|---|
| Memory fit | 25.0 / 25 | |
| Speed | 3.0 / 15 | |
| Memory use | 1.4 / 15 | |
| Match score | 52.8 / 100 |
Every precision on the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)
| Quant | Memory needed | Available | Speed | Memory mode | Runs | Quality | Download |
|---|---|---|---|---|---|---|---|
FP16 | 14.0 GB | 230 GB | 4.1 min | Everything on GPU | Very slow | 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Original weights (opens in a new tab) |
FP8 | 8.1 GB | 230 GB | 3.7 min | Everything on GPU | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Original weights (opens in a new tab) |
Other hardware that runs it
-
50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4070 SUPER
-
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
AMD Radeon RX 7900 XTX
-
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 3090
-
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4090
-
50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
AMD Radeon RX 9070 XT
-
50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4070 Ti SUPER
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.