Runway / GPUStack
Stable Diffusion 1.5 (GGUF)
SD 1.5 in single-file GGUF format. Alternative to CoreML. Uses stable-diffusion.cpp with Metal acceleration.
Check Your Hardware
See which quantizations of Stable Diffusion 1.5 (GGUF) your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| Q4_0 | 4 | 1.75 GB | 2.5 GB | 4 GB | 80% |
| Q8_0 | 8 | 1.88 GB | 3 GB | 4.5 GB | 95% |
Try It — Diffusion Generation Demo
Click "Generate" to watch how Flux.1 creates an image from noise. Real outputs from RunThisModel.com.
"A cozy wooden cabin in snowy mountains at golden hour sunset"
"A friendly humanoid robot reading a book in a library"
"Gourmet sushi platter, professional food photography"
"Woman scientist in a modern lab, natural lighting"
"Snow leopard on mountain peak at dawn, golden rim light"
"Cyberpunk city at night, neon signs, rain reflections"
Animation simulates the diffusion denoising process at recorded generation speed. Actual generation requires GPU hardware or cloud service.
Frequently Asked Questions
How much VRAM do I need to run Stable Diffusion 1.5 (GGUF)?
Stable Diffusion 1.5 (GGUF) requires 2.5GB VRAM minimum with Q4_0 quantization. For full precision, you need 3GB VRAM.
What is the best quantization for Stable Diffusion 1.5 (GGUF)?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.