Can My GPU Run Stable Diffusion 3.5 Large (8B)?
Text to Image · VRAM requirements and compatibility for 78 GPUs
Home › AI Models › Stable Diffusion 3.5 Large (8B)
Generate top-quality images from text prompts. Stable Diffusion 3.5 Large (8B) is a text to image model — developed by Stability AI, released 2024-10, 8B parameters, 16.3 GB download, license: stabilityai-community.
Short answer: you need at least 6 GB of VRAM (12 GB recommended). 78 of 78 GPUs can run it; the smallest NVIDIA card that can is the GTX 1060 6GB (6 GB).
Check Stable Diffusion 3.5 Large (8B) on your GPUStable Diffusion 3.5 Large (8B) VRAM requirements
| Format | VRAM |
|---|---|
| FP16 (full precision) | 18 GB |
| FP8 | 10 GB |
| GGUF Q4 | 7 GB |
| GGUF Q3 | 6 GB |
| Minimum | 6 GB |
| Recommended | 12 GB |
| Optimal | 24 GB |
Tip: Best SD3 quality. FP8 or GGUF recommended for <16GB GPUs.
Available as: ComfyUI, Diffusers, GGUF quantized versions, FP8 versions, CPU offloading.
Official pages: Hugging Face
Which GPUs can run Stable Diffusion 3.5 Large (8B)?
Ratings go from S (perfect) to F (can't run) and use the best format that fits in each card's VRAM. How ratings work.
NVIDIA
| GPU | VRAM | Rating | Runs as | Speed | |
|---|---|---|---|---|---|
| RTX 5090 | 32 GB | Perfect | FP16 | Fast | Details |
| RTX 5080 | 16 GB | Great | FP8 | Fast | Details |
| RTX 5070 Ti | 16 GB | Great | FP8 | Fast | Details |
| RTX 5070 | 12 GB | Good | FP8 | Moderate | Details |
| RTX 5060 Ti 16GB | 16 GB | Good | FP8 | Moderate | Details |
| RTX 5060 Ti 8GB | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 5060 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 4090 | 24 GB | Great | FP16 | Fast | Details |
| RTX 4080 Super | 16 GB | Great | FP8 | Fast | Details |
| RTX 4080 | 16 GB | Great | FP8 | Fast | Details |
| RTX 4070 Ti Super | 16 GB | Great | FP8 | Fast | Details |
| RTX 4070 Ti | 12 GB | Good | FP8 | Moderate | Details |
| RTX 4070 Super | 12 GB | Good | FP8 | Moderate | Details |
| RTX 4070 | 12 GB | Good | FP8 | Moderate | Details |
| RTX 4060 Ti 16GB | 16 GB | Good | FP8 | Moderate | Details |
| RTX 4060 Ti 8GB | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 4060 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 3090 Ti | 24 GB | Great | FP16 | Fast | Details |
| RTX 3090 | 24 GB | Good | FP16 | Fast | Details |
| RTX 3080 Ti | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 3080 12GB | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 3080 10GB | 10 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 3070 Ti | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 3070 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 3060 Ti | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 5050 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 3060 | 12 GB | Good | GGUF Q4 | Slow | Details |
| RTX 2080 Ti | 11 GB | Good | GGUF Q4 | Slow | Details |
| RTX 2080 Super | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 2080 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 2070 Super | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 2070 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 2060 Super | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 2060 | 6 GB | Barely | GGUF Q3 | Very Slow | Details |
| GTX 1080 Ti | 11 GB | Usable | GGUF Q4 | Slow | Details |
| GTX 1080 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| GTX 1070 Ti | 8 GB | Usable | GGUF Q4 | Slow | Details |
| GTX 1070 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| GTX 1060 6GB | 6 GB | Barely | GGUF Q3 | Very Slow | Details |
AMD
| GPU | VRAM | Rating | Runs as | Speed | |
|---|---|---|---|---|---|
| RX 9070 XT | 16 GB | Good | FP8 | Fast | Details |
| RX 9070 | 16 GB | Good | FP8 | Moderate | Details |
| RX 7900 XTX | 24 GB | Good | FP16 | Fast | Details |
| RX 9070 GRE | 12 GB | Good | FP8 | Moderate | Details |
| RX 7900 XT | 20 GB | Good | FP16 | Moderate | Details |
| RX 9060 XT 16GB | 16 GB | Good | FP8 | Moderate | Details |
| RX 9060 XT 8GB | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RX 7900 GRE | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RX 7800 XT | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RX 7700 XT | 12 GB | Good | GGUF Q4 | Slow | Details |
| RX 7600 XT | 16 GB | Good | GGUF Q4 | Slow | Details |
| RX 7600 | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RX 6950 XT | 16 GB | Good | GGUF Q4 | Slow | Details |
| RX 6900 XT | 16 GB | Good | GGUF Q4 | Slow | Details |
| RX 6800 XT | 16 GB | Good | GGUF Q4 | Slow | Details |
| RX 6800 | 16 GB | Good | GGUF Q4 | Slow | Details |
| RX 6700 XT | 12 GB | Usable | GGUF Q4 | Slow | Details |
| RX 6600 XT | 8 GB | Usable | GGUF Q4 | Slow | Details |
| RX 6600 | 8 GB | Usable | GGUF Q4 | Slow | Details |
Apple
| GPU | VRAM | Rating | Runs as | Speed | |
|---|---|---|---|---|---|
| M5 Ultra | 96 GB | Usable | FP16 | Fast | Details |
| M3 Ultra | 96 GB | Usable | FP16 | Fast | Details |
| M4 Max | 48 GB | Usable | FP16 | Fast | Details |
| M5 Max | 48 GB | Usable | FP16 | Fast | Details |
| M4 Pro | 24 GB | Barely | FP16 | Moderate | Details |
| M5 Pro | 24 GB | Barely | FP16 | Moderate | Details |
| M4 | 16 GB | Barely | GGUF Q4 | Slow | Details |
| M3 Max | 36 GB | Barely | FP16 | Moderate | Details |
| M3 Pro | 18 GB | Can't Run | FP16 | Slow | Details |
| M5 | 16 GB | Barely | GGUF Q4 | Slow | Details |
| M6 | 16 GB | Barely | GGUF Q4 | Slow | Details |
| M3 | 16 GB | Barely | GGUF Q4 | Slow | Details |
| M2 Ultra | 192 GB | Usable | FP16 | Fast | Details |
| M2 Max | 96 GB | Usable | FP16 | Fast | Details |
| M2 Pro | 32 GB | Barely | FP16 | Moderate | Details |
| M2 | 24 GB | Barely | FP16 | Slow | Details |
| M1 Ultra | 128 GB | Usable | FP16 | Fast | Details |
| M1 Max | 64 GB | Usable | FP16 | Moderate | Details |
| M1 Pro | 32 GB | Barely | FP16 | Moderate | Details |
| M1 | 16 GB | Barely | GGUF Q4 | Slow | Details |
Frequently asked questions
How much VRAM does Stable Diffusion 3.5 Large (8B) need?
Stable Diffusion 3.5 Large (8B) needs at least 6 GB of VRAM, 12 GB recommended, and 18 GB to run at full FP16 precision.
Can Stable Diffusion 3.5 Large (8B) run on 8 GB of VRAM (e.g. NVIDIA RTX 4060)?
On the NVIDIA RTX 4060: yes, in GGUF Q4 (rating C, usable).
Can Stable Diffusion 3.5 Large (8B) run on the NVIDIA RTX 3060 (12 GB)?
Yes, in GGUF Q4 (rating B, good).
Which GPUs can run Stable Diffusion 3.5 Large (8B)?
78 of the 78 GPUs we track can run it, and 34 run it well (rating B or better). The cheapest one that runs it well is the NVIDIA RTX 3060 (12 GB, about $329).
Does Stable Diffusion 3.5 Large (8B) work on AMD or Apple Silicon?
19 AMD Radeon and 20 Apple Silicon chips in our list can run it. There is no MPS backend, so it may not work on Apple Silicon.