Can the RTX 5070 12 GB run Stable Diffusion 3.5 Medium?
Yes. 16-bit fits on the RTX 5070 12 GB with 5.1 GB to spare.
Take 16-bit (5.1 GB). In use it comes to about 6.9 GB, with 5.1 GB left over on 12 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | sd3.5_medium.safetensors 16-bit · stabilityai/stable-diffusion-3.5-medium | models/diffusion_models | 5.1 GB | Download → |
| Text encoder | t5xxl_fp8_e4m3fn.safetensors T5-XXL FP8 · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 4.9 GB | Download → |
| Text encoder | clip_l.safetensors CLIP-L · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 0.2 GB | Download → |
| Text encoder | clip_g.safetensors CLIP-G · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 1.4 GB | Download → |
| VAE | diffusion_pytorch_model.safetensors SD 3.5 VAE (gated repo: log in and accept the licence first) · stabilityai/stable-diffusion-3.5-medium | models/vae | 0.2 GB | Download → |
| Total download · keep about the same free on disk | 11.8 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). Sizes from Hugging Face, 2026-10-01.
02Every SD 3.5 Medium file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · stabilityai | 5.1 GB | 6.9 GB | fits · 5.1 GB spare | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 2.9 GB | 4.7 GB | fits · 7.3 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 2.3 GB | 4.1 GB | fits · 7.9 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 2.1 GB | 3.9 GB | fits · 8.1 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 1.8 GB | 3.6 GB | fits · 8.4 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 1.5 GB | 3.3 GB | fits · 8.7 GB spare | noticeable loss of detail | Hugging Face → |
“Needed” adds 1 GB of working memory for SD 3.5 Medium and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run SD 3.5 Medium on a RTX 5070 12 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 5070 12 GB
The RTX 5070 12 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.
12 GB GDDR7 · 192-bit · 672 GB/s · Blackwell. Everything that runs on it →
05Questions
How much VRAM does SD 3.5 Medium need?
Around 3.3 GB with the smallest file (Q3_K_M) and 4.7 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 6.9 GB.
Which SD 3.5 Medium file should I download for the RTX 5070 12 GB?
16-bit (5.1 GB) from stabilityai/stable-diffusion-3.5-medium.
How much do I need to download for SD 3.5 Medium on the RTX 5070 12 GB?
11.8 GB: sd3.5_medium.safetensors, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, clip_g.safetensors, diffusion_pytorch_model.safetensors.