Can the RTX 5060 Ti 16 GB run Qwen-Image?
Download Q4_K_M (13.1 GB). With the model's working memory it needs about 15.9 GB, leaving 0.1 GB spare on 16 GB. Quality: good; some loss in fine detail and text. For better quality, Q5_K_M (14.9 GB) also runs, with about 1.7 GB spilling into system RAM — a little slower, still practical.
Worth trying on this GPU: with an up-to-date ComfyUI, Dynamic VRAM (on by default for NVIDIA since March 2026) streams whatever does not fit from system RAM, and ComfyUI's own start-up message recommends native FP8/INT8 files over GGUF, saying they “will be faster even if they are larger than your memory”. So before settling for a heavily compressed GGUF, try the native FP8 file (20.4 GB). The file recommended above is the best one that fits entirely — the safe choice on older ComfyUI versions, AMD and Intel. Comfy blog: Dynamic VRAM →
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | qwen-image-Q4_K_M.gguf Q4_K_M · city96/Qwen-Image-gguf | models/unet | 13.1 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 | 22.7 GB | |||
Alternatives: Qwen2.5-VL 7B BF16 (16.6 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 22.7 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 28.7 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every Qwen-Image file on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 40.9 GB | 43.7 GB | 27.7 GB too big | the original weights | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 20.4 GB | 23.2 GB | 7.2 GB too big | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · city96 | 21.8 GB | 24.6 GB | 8.6 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 16.8 GB | 19.6 GB | 3.6 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 14.9 GB | 17.7 GB | spills 1.7 GB | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · city96 | 13.1 GB | 15.9 GB | fits · 0.1 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 9.7 GB | 12.5 GB | fits · 3.5 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 7.1 GB | 9.9 GB | fits · 6.1 GB spare | heavy loss; a last resort | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 2 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
Qwen2.5-VL 7B: 16.6 GB as 16-bit, 9.4 GB as FP8. 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 16 GB the FP8 encoder fits on its own, so prompt encoding stays fast.
04About this GPU
The RTX 5060 Ti 16 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.
RTX 5060 Ti 16 GB: 16 GB GDDR7 · 128-bit · 448 GB/s · Blackwell. Everything that runs on the RTX 5060 Ti 16 GB →
05What more VRAM would change
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 5060 Ti 16 GB to the RTX 3090 24 GB → · What changes from the RTX 5060 Ti 16 GB to the RTX 5070 Ti 16 GB → · What changes from the RTX 5060 Ti 16 GB to the RTX 4090 24 GB → · What changes from the RTX 5060 Ti 16 GB to the RTX 5090 32 GB →
06Measured and reported results
This is my own card. Timed runs (seconds per image, peak VRAM) from a benchmark script are being added. Until then this page is calculated like every other.
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), counting working memory and a small system reserve. The full 16-bit file needs about 43.7 GB.
Which Qwen-Image file should I download for the RTX 5060 Ti 16 GB?
Q4_K_M (13.1 GB) from city96/Qwen-Image-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
Is FP8 faster than GGUF on the RTX 5060 Ti 16 GB?
It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.
How much do I need to download for Qwen-Image on the RTX 5060 Ti 16 GB?
About 22.7 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 16 GB card, 32 GB of system RAM or more is recommended.