P-H3-Image-Comfy
bf16, int8 and w4a8 · From 21 GB of VRAM · 8 steps · Text-to-image and editing with up to 8 images
Params
—
Context
—
Downloads 30d
704 K
Likes
266
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)704 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | fp16 | 139.3 GB | 153.8 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Licence
- other
- First seen on the Hub
- 2026-10-28
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-06
Compare with any text-to-image model