Stable Diffusion 3.5 Large on Apple M2 (8GB Unified)
M2 (8GB Unified) cannot run Stable Diffusion 3.5 Large. 8 GB VRAM is insufficient at any quantization level.
Model Size
8.1B
Device VRAM
8 GB
Bandwidth
100 GB/s
Quantization
FP16
Performance by Quantization
OwnRig currently has one published compatibility entry for Stable Diffusion 3.5 Large on Apple M2 (8GB Unified) at FP16. This pairing has limitations — check the rating and notes below.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| FP16 | – | – | ✗ Offload | Not viable | estimated |
Notes
FP16
Smallest quantization requires more than the ~5.5GB available on this 8GB Mac.
About Stable Diffusion 3.5 Large
Stable Diffusion 3.5 Large (8.1B) is a image gen model. Latest Stable Diffusion architecture with significantly improved prompt adherence, typography, and composition over SDXL. Higher VRAM requirement (12GB+ at FP16) but produces noticeably better images. The current standard for local image generation.
View all Stable Diffusion 3.5 Large hardware options →About Apple M2 (8GB Unified)
Apple M2 (8GB Unified) has 8 GB at 100 GB/s. Available in MacBook Air 13" (2022), MacBook Air 15" (2023), MacBook Pro 13" (2022).
See all models Apple M2 (8GB Unified) can run →Estimate method: Estimated: model exceeds 8GB Mac usable VRAM. Reference hardware source: github.com (2026-04-18)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.