Z-Image (base) on 16 GB of VRAM
Yes, but only just: 16-bit leaves 1.7 GB free on 16 GB. The undistilled base of Z-Image Turbo: same 6B size, but 28–50 steps with CFG. Better for LoRA training and negative prompts.
Runs well
Yes, just.
16-bit (12.3 GB) fits with only 1.7 GB to spare (about 14.3 GB of 16 GB).
Best file16-bit
File size12.3 GB
VRAM needed~14.3 GB
System RAM32 GB+
Memory map · 16 GB GPU14.3 GB / 16 GB
08 GB16 GB
Weights 16-bit · 12.3 GBWorking memory · 1.2 GBReserve · 0.8 GBFree · 1.7 GB
calculated How this is counted.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | z_image_bf16.safetensors 16-bit · Comfy-Org/z_image | models/diffusion_models | 12.3 GB | Download → |
| Text encoder | qwen_3_4b_fp8_mixed.safetensors Qwen3 4B FP8 · Comfy-Org/z_image | models/text_encoders | 5.6 GB | Download → |
| VAE | ae.safetensors FLUX.1 VAE (ae) · Comfy-Org/z_image | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 18.3 GB | |||
Alternatives: Qwen3 4B BF16 (8.0 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: 16-bit workflow (.json). Drag the file into ComfyUI. All workflows →
02Every file, on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 12.3 GB | 14.3 GB | fits · 1.7 GB spare | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 7.2 GB | 9.2 GB | fits · 6.8 GB spare | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 6.2 GB | 8.2 GB | fits · 7.8 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 6.1 GB | 8.1 GB | fits · 7.9 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 5.6 GB | 7.6 GB | fits · 8.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 5.1 GB | 7.1 GB | fits · 8.9 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 4.6 GB | 6.6 GB | fits · 9.4 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 4.0 GB | 6.0 GB | fits · 10.0 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.2 GB of working memory for Z-Image and a 0.8 GB reserve. Sizes 2026-10-01.