Views
No views yet
asym_w4a8_int8 quantized-diffusion format (Comfy Kitchen).| File | Size | Notes |
|---|---|---|
z_image_turbo_w4a8.safetensors | 3.5 GB | Diffusion model, asym_w4a8_int8, group_size 16 + ConvRot |
qwen_3_4b_w4a8.safetensors | 2.8 GB | Qwen3-4B text encoder, asym_w4a8_int8, group_size 16 + ConvRot |
models directory:ComfyUI/
├── models/
│ ├── diffusion_models/
│ │ └── z_image_turbo_w4a8.safetensors
│ ├── text_encoders/
│ │ └── qwen_3_4b_w4a8.safetensors
│ └── vae/
│ └── flux1-vae.safetensorsLoad Diffusion Model node pointed at z_image_turbo_w4a8.safetensors and a Load CLIP node
pointed at qwen_3_4b_w4a8.safetensors..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).| Model | Steps | Sample time |
|---|---|---|
| BF16 | 8 | ~14 s |
| W4A8 (this repo) | 8 | ~7 s |
| int8_convrot (official) | 8 | ~6 s |
<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": ...}cap_embedder.1 are kept in BF16.