Can the RTX 3080 10 GB run ERNIE-Image (Turbo)?
Not at full quality. The 16-bit and 8-bit files are too big for the RTX 3080 10 GB; the largest that fits is Q6_K (6.8 GB).
Q6_K (6.8 GB) fits with only 0.9 GB to spare (about 9.1 GB of 10 GB). Quality: very close to the original. For better quality, Q8_0 (8.7 GB) also runs, with about 1.0 GB spilling into system RAM - a little slower, still practical.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | ernie-image-turbo-Q6_K.gguf Q6_K · unsloth/ERNIE-Image-Turbo-GGUF | models/unet | 6.8 GB | Download → |
| Text encoder | ministral-3-3b.safetensors Ministral 3 3B · Comfy-Org/ERNIE-Image | models/text_encoders | 7.7 GB | Download → |
| VAE | flux2-vae.safetensors FLUX.2 VAE · Comfy-Org/ERNIE-Image | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 14.8 GB | |||
Only for some workflows: ERNIE prompt enhancer (optional) (6.9 GB). Sizes from Hugging Face, 2026-10-01.
02Every ERNIE-Image file on 10 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 16.1 GB | 18.4 GB | 8.4 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 8.7 GB | 11.0 GB | spills 1.0 GB | practically identical to the original | Hugging Face → |
| Q6_K ← GGUF · unsloth | 6.8 GB | 9.1 GB | fits · 0.9 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 5.9 GB | 8.2 GB | fits · 1.8 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 5.0 GB | 7.3 GB | fits · 2.7 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 3.9 GB | 6.2 GB | fits · 3.8 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 3.2 GB | 5.5 GB | fits · 4.5 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.5 GB of working memory for ERNIE-Image 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 ERNIE-Image on a RTX 3080 10 GB, send your time per image and peak VRAM and it will appear here, credited.
04With more VRAM
With 12 GB you could run ERNIE-Image at 8-bit or better (Q8_0, 8.7 GB) with no offloading: for example on the RTX 5070 12 GB, RTX 4070 Super 12 GB, RTX 4070 12 GB.
What changes from the RTX 3080 10 GB to the RTX 3090 24 GB → · What changes from the RTX 3080 10 GB to the RTX 5070 Ti 16 GB →
05About the RTX 3080 10 GB
The RTX 3080 10 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain - Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.
10 GB GDDR6X · 320-bit · 760 GB/s · Ampere. Everything that runs on it →
06Questions
How much VRAM does ERNIE-Image need?
Around 5.5 GB with the smallest file (Q2_K) and 11.0 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 18.4 GB.
Which ERNIE-Image file should I download for the RTX 3080 10 GB?
Q6_K (6.8 GB) from unsloth/ERNIE-Image-Turbo-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
How much do I need to download for ERNIE-Image on the RTX 3080 10 GB?
14.8 GB: ernie-image-turbo-Q6_K.gguf, ministral-3-3b.safetensors, flux2-vae.safetensors.