Can the RTX 3080 10 GB run Qwen-Image?
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 Q2_K (7.1 GB).
Q2_K (7.1 GB) fits with only 0.1 GB to spare (about 9.9 GB of 10 GB). Quality: heavy loss; a last resort.
Also try the FP8 file (20.4 GB) on this GPU. It does not fit entirely, but a current ComfyUI streams the overflow from RAM and native 8-bit files often beat a small GGUF that does fit. Dynamic VRAM →
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | qwen-image-Q2_K.gguf Q2_K · city96/Qwen-Image-gguf | models/unet | 7.1 GB | Download → |
| Text encoder | qwen_2.5_vl_7b_fp8_scaled.safetensors Qwen2.5-VL 7B FP8 · Comfy-Org/Qwen-Image_ComfyUI | models/text_encoders | 9.4 GB | Download → |
| VAE | qwen_image_vae.safetensors Qwen-Image VAE · Comfy-Org/Qwen-Image_ComfyUI | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 16.7 GB | |||
Alternatives: Qwen2.5-VL 7B BF16 (16.6 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: GGUF Q4_K_M workflow (.json). Drag the file into ComfyUI. All workflows →
02Every Qwen-Image file on 10 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 40.9 GB | 43.7 GB | 33.7 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 21.8 GB | 24.6 GB | 14.6 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 20.4 GB | 23.2 GB | 13.2 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 16.8 GB | 19.6 GB | 9.6 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 14.9 GB | 17.7 GB | 7.7 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 13.1 GB | 15.9 GB | 5.9 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 9.7 GB | 12.5 GB | 2.5 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K ← GGUF · city96 | 7.1 GB | 9.9 GB | fits · 0.1 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 2 GB of working memory for Qwen-Image and a 0.8 GB reserve. Sizes 2026-10-01.
03The text encoder
At 9.4 GB even the smallest Qwen2.5-VL 7B file is too big for 10 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 16.6 GB, FP8 9.4 GB. Why the encoder does not count against VRAM →
04Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Qwen-Image on a RTX 3080 10 GB, send your time per image and peak VRAM and it will appear here, credited.
05With more VRAM
With 24 GB you could run Qwen-Image at 8-bit or better (FP8, 20.4 GB) with no offloading: for example on the RTX 4090 24 GB, RTX 3090 24 GB, RX 7900 XTX 24 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 →
06About 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 →
07Questions
How much VRAM does Qwen-Image need?
Around 9.9 GB with the smallest file (Q2_K) and 23.2 GB with an 8-bit file (FP8). The full 16-bit file needs about 43.7 GB.
Which Qwen-Image file should I download for the RTX 3080 10 GB?
Q2_K (7.1 GB) from city96/Qwen-Image-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for Qwen-Image on the RTX 3080 10 GB?
Q8_0 (21.8 GB). The RTX 3080 10 GB has no FP8 maths, so FP8 (20.4 GB) only saves memory and is a step further from the original.
How much do I need to download for Qwen-Image on the RTX 3080 10 GB?
16.7 GB: qwen-image-Q2_K.gguf, qwen_2.5_vl_7b_fp8_scaled.safetensors, qwen_image_vae.safetensors.