Z-Image-Turbo-W4A8

Z-Image-Turbo W4A8

W4A8 (4-bit weight, 8-bit activation) quantized weights for Z-Image-Turbo, made for ComfyUI using ComfyUI's native asym_w4a8_int8 quantized-diffusion format (Comfy Kitchen).

Both the diffusion model and the Qwen3-4B text encoder are quantized, so the whole pipeline fits in low VRAM.

Files

Original BF16 sizes: diffusion 12.3 GB, text encoder 8.0 GB.

Usage (ComfyUI)

Place the files in your ComfyUI models directory:

ComfyUI/
├── models/
│   ├── diffusion_models/
│   │   └── z_image_turbo_w4a8.safetensors
│   ├── text_encoders/
│   │   └── qwen_3_4b_w4a8.safetensors
│   └── vae/
│       └── flux1-vae.safetensors

Then use the standard Z-Image-Turbo text-to-image workflow with a Load Diffusion Model node pointed at z_image_turbo_w4a8.safetensors and a Load CLIP node pointed at qwen_3_4b_w4a8.safetensors.

Both files are detected automatically by ComfyUI (.comfy_quant metadata keys); no custom nodes are required. The text encoder must be loaded through the Qwen3-4B / Z-Image CLIP path (it does not need the pooled output).

Quality & Speed

Verified on an 8 GB VRAM GPU (RTX 4060 Laptop) at 1024x1024, 8 sampling steps:

Image quality is visually identical between BF16, W4A8 and the official int8_convrot checkpoint.

Quantization format

Per quantized Linear layer the file stores:

• <key>.weight — int8, ConvRot-rotated packed int4 [N, K/2]
• <key>.weight_s_rel — fp8 e4m3fn group scale [N, K/group_size]
• <key>.weight_s_channel — fp32 channel scale [N]
• <key>.weight_codebook — fp32 Lloyd-Max codebook [16]
• <key>.comfy_quant — uint8 JSON {"format": "asym_w4a8_int8", "group_size": 16, "convrot_groupsize": ...}

1D norms, biases, the embedding table and cap_embedder.1 are kept in BF16.