Can the RX 9070 XT 16 GB run Qwen-Image?
Not at full quality. The 16-bit and 8-bit files are too big for the RX 9070 XT 16 GB; the largest that fits is Q4_K_M (13.1 GB).
Q4_K_M (13.1 GB) fits with only 0.1 GB to spare (about 15.9 GB of 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.
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). 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 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 → |
“Needed” adds 2 GB of working memory for Qwen-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 Qwen-Image on a RX 9070 XT 16 GB, send your time per image and peak VRAM and it will appear here, credited.
04With 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.
05About the RX 9070 XT 16 GB
ComfyUI supports AMD GPUs on Windows officially since v0.7.0 (January 2026), through ROCm. Memory works the same as on NVIDIA, so the fit verdicts apply. Some custom nodes are NVIDIA-only. RX 9000 (RDNA 4) GPUs have FP8 hardware, and ComfyUI computes FP8 natively on them with PyTorch 2.7+ and ROCm 6.4+.
16 GB GDDR6 · 256-bit · 640 GB/s · RDNA 4. Everything that runs on it →
06Questions
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 RX 9070 XT 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.
FP8 or Q8_0 for Qwen-Image on the RX 9070 XT 16 GB?
FP8 (20.4 GB): the RX 9070 XT 16 GB computes it natively, while Q8_0 (21.8 GB) is unpacked on the fly.
How much do I need to download for Qwen-Image on the RX 9070 XT 16 GB?
22.7 GB: qwen-image-Q4_K_M.gguf, qwen_2.5_vl_7b_fp8_scaled.safetensors, qwen_image_vae.safetensors.