Stable Diffusion 3.5 Large on 6 GB of VRAM
Nothing fits entirely, but Q4_1 (5.3 GB) overflows by only about 1.6 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | sd3.5_large-Q4_1.gguf Q4_1 · city96/stable-diffusion-3.5-large-gguf | models/unet | 5.3 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 → |
| Total download · keep about the same free on disk | 11.8 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 11.8 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 17.8 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every file, on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · stabilityai | 16.5 GB | 18.8 GB | 12.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 8.8 GB | 11.1 GB | 5.1 GB too big | practically identical to the original | Hugging Face → |
| Q5_1 GGUF · city96 | 6.3 GB | 8.6 GB | 2.6 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_1 ← GGUF · city96 | 5.3 GB | 7.6 GB | spills 1.6 GB | good; some loss in fine detail and text | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.5 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
CLIP-L + CLIP-G + T5-XXL: 9.8 GB as 16-bit, 4.9 GB as FP8 (T5-XXL sizes shown; CLIP-L and CLIP-G add about 1.6 GB). ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 6 GB the FP8 encoder fits on its own, so prompt encoding stays fast.