Z-Image Turbo is an image generation model by Alibaba (Tongyi) (6.15B; text encoder: Qwen3-4B). Lightweight and fast with few steps; officially fits in 16 GB.
Change precision, resolution →
| Precision | Model size | 1024×1024 | 1536×1536 |
|---|---|---|---|
| BF16 / FP16 (uncompressed) | 12.3 GB | 13.5 GB all in VRAM 18.1 GB | 14.4 GB all in VRAM 19.0 GB |
| FP8 (half size, near-lossless) | 6.3 GB | 7.5 GB all in VRAM 12.1 GB | 8.4 GB all in VRAM 13.0 GB |
| GGUF Q8_0 (similar to FP8) | 6.6 GB | 7.8 GB all in VRAM 12.4 GB | 8.7 GB all in VRAM 13.3 GB |
| GGUF Q4_K_S (popular low-VRAM choice) | 3.7 GB | 4.9 GB all in VRAM 9.5 GB | 5.8 GB all in VRAM 10.4 GB |
Bold = VRAM needed when ComfyUI swaps the text encoder and the model. "All in VRAM" = keeping both loaded. Text encoder assumed at FP8. Official: fits on 16 GB consumer GPUs (measured with the official implementation).
| GPU | VRAM | Best precision | VRAM needed | Verdict | Buy |
|---|---|---|---|---|---|
| RTX 4060 previous gen | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 4060 Ti 8GB previous gen | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7600 previous gen | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 5050 | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 5060 Ti 8GB | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 5060 | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 3070 previous gen | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 3060 Ti previous gen | 8 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 3080 (10GB) previous gen | 10 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 2080 Ti previous gen | 11 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 3060 12GB previous gen | 12 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 6700 XT previous gen | 12 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| Intel Arc B580 | 12 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 4070 Ti previous gen | 12 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 4070 / SUPER previous gen | 12 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 5070 | 12 GB | FP8 | 7.5 GB | ○ Runs with model swapping | Check price |
| RTX 4060 Ti 16GB previous gen | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7600 XT previous gen | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9060 XT 16GB | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| RTX 5060 Ti 16GB | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 6800 previous gen | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7800 XT previous gen | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9070 XT | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9070 | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| RTX 4070 Ti SUPER previous gen | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| RTX 4080 previous gen | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| RTX 4080 SUPER previous gen | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| RTX 5070 Ti | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| RTX 5080 | 16 GB | BF16 / FP16 | 13.5 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7900 XT previous gen | 20 GB | BF16 / FP16 | 13.5 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 3090 previous gen | 24 GB | BF16 / FP16 | 13.5 GB | ◎ Fits entirely in VRAM | Check price |
| Radeon RX 7900 XTX previous gen | 24 GB | BF16 / FP16 | 13.5 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 4090 previous gen | 24 GB | BF16 / FP16 | 13.5 GB | ◎ Fits entirely in VRAM | Check price |
| RTX 5090 | 32 GB | BF16 / FP16 | 13.5 GB | ◎ Fits entirely in VRAM | Check price |
ComfyUI also runs on AMD Radeon (ROCm) and Intel Arc, but setup is harder than on NVIDIA and some features (such as FP8 acceleration) are not supported.
→ Image & Video AI VRAM Calculator (all 15 models) / Local LLM VRAM Calculator
Estimates for ComfyUI, about ±20%. Model specs from the publisher's config files and released file sizes (checked October 2026).