Stable Diffusion 3.5 Large is an image generation model by Stability AI (8.1B; text encoder: CLIP-L・CLIP-G + T5-XXL).
Change precision, resolution →
| Precision | Model size | 1024×1024 | 1536×1536 |
|---|---|---|---|
| BF16 / FP16 (uncompressed) | 16.2 GB | 17.4 GB all in VRAM 23.5 GB | 18.2 GB all in VRAM 24.3 GB |
| FP8 (half size, near-lossless) | 8.3 GB | 9.4 GB all in VRAM 15.6 GB | 10.2 GB all in VRAM 16.4 GB |
| GGUF Q8_0 (similar to FP8) | 8.7 GB | 9.8 GB all in VRAM 16.0 GB | 10.6 GB all in VRAM 16.8 GB |
| GGUF Q5_K_S | 5.8 GB | 6.9 GB all in VRAM 13.1 GB | 7.7 GB all in VRAM 13.9 GB |
| GGUF Q4_K_S (popular low-VRAM choice) | 4.9 GB | 6.2 GB all in VRAM 12.2 GB | 6.8 GB all in VRAM 13.0 GB |
Bold = VRAM needed when ComfyUI swaps the text encoder and the model. "All in VRAM" = keeping both loaded. Text encoder assumed at FP8.
| GPU | VRAM | Best precision | VRAM needed | Verdict | Buy |
|---|---|---|---|---|---|
| RTX 4060 previous gen | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| RTX 4060 Ti 8GB previous gen | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7600 previous gen | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| RTX 5050 | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| RTX 5060 Ti 8GB | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| RTX 5060 | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| RTX 3070 previous gen | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| RTX 3060 Ti previous gen | 8 GB | GGUF Q5_K_S | 6.9 GB | ○ Runs with model swapping | Check price |
| RTX 3080 (10GB) previous gen | 10 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| RTX 2080 Ti previous gen | 11 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| RTX 3060 12GB previous gen | 12 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| Radeon RX 6700 XT previous gen | 12 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| Intel Arc B580 | 12 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| RTX 4070 Ti previous gen | 12 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| RTX 4070 / SUPER previous gen | 12 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| RTX 5070 | 12 GB | FP8 | 9.4 GB | ○ Runs with model swapping | Check price |
| RTX 4060 Ti 16GB previous gen | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 7600 XT previous gen | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 9060 XT 16GB | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 5060 Ti 16GB | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 6800 previous gen | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 7800 XT previous gen | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 9070 XT | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 9070 | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 4070 Ti SUPER previous gen | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 4080 previous gen | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 4080 SUPER previous gen | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 5070 Ti | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 5080 | 16 GB | FP8 | 9.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 7900 XT previous gen | 20 GB | BF16 / FP16 | 17.4 GB | ○ Runs with model swapping | Check price |
| RTX 3090 previous gen | 24 GB | BF16 / FP16 | 17.4 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 7900 XTX previous gen | 24 GB | BF16 / FP16 | 17.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 4090 previous gen | 24 GB | BF16 / FP16 | 17.4 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 5090 | 32 GB | BF16 / FP16 | 17.4 GB | ◎ Fits entirely in VRAM | Check price |
ComfyUI also runs on AMD Radeon (ROCm) and Intel Arc, but setup is harder than on NVIDIA and some features (such as FP8 acceleration) are not supported.
→ Image & Video AI VRAM Calculator (all 15 models) / Local LLM VRAM Calculator
Estimates for ComfyUI, about ±20%. Model specs from the publisher's config files and released file sizes (checked October 2026).