Qwen-Image on 24 GB of VRAM
Yes, but only just: FP8 leaves 0.8 GB free on 24 GB. Alibaba's 20B text-to-image model, known for rendering long text and posters well. Big: the 8-bit file alone is over 20 GB.
FP8 (20.4 GB) fits with only 0.8 GB to spare (about 23.2 GB of 24 GB).
Got an RTX 40 or 50? Swap Q8_0 for FP8 (20.4 GB): same quality class, computed natively there.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | qwen_image_fp8_e4m3fn.safetensors FP8 · Comfy-Org/Qwen-Image_ComfyUI | models/diffusion_models | 20.4 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 | 30.1 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 →
System RAM: 48 GB or more. These files take about 30.1 GB of RAM while loaded, 36.1 GB with Windows and ComfyUI. What happens with less. calculated
02Every file, on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 40.9 GB | 43.7 GB | 19.7 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 21.8 GB | 24.6 GB | spills 0.6 GB | practically identical to the original | Hugging Face → |
| FP8 ← SAFETENSORS · Comfy-Org | 20.4 GB | 23.2 GB | fits · 0.8 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 16.8 GB | 19.6 GB | fits · 4.4 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 14.9 GB | 17.7 GB | fits · 6.3 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 13.1 GB | 15.9 GB | fits · 8.1 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 9.7 GB | 12.5 GB | fits · 11.5 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 7.1 GB | 9.9 GB | fits · 14.1 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.