Downloads · 30 days
0
Kroma-INT8-Quants
PotatoForge/Kroma-INT8-Quants
Kroma-INT8-Quants is a text-to-image model from PotatoForge. Use it when you need an image from a text prompt.
Experimental INT8 quantizations of Kroma (by lodestones), primarily targeting lower-VRAM and older consumer GPUs.
Access
Public
Updated Sep 11, 2026
Repo size
44.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors44.6 GB · 100%
At a glance
- Task
- Text-to-Image
- Access
- Public
- Created
- Aug 9, 2026
- Updated
- Sep 11, 2026
- SHA
- 8e7e27ee
Base models
Model card
From the Hugging Face model README
Kroma INT8 Quants
Experimental INT8 quantizations of Kroma (by lodestones), primarily targeting lower-VRAM and older consumer GPUs.
Available Versions
| Version | File Name | File Size |
|---|---|---|
| v0.1 | kroma_v0.1_turbo_v0.1.safetensors | 8.67 GB |
| Mixed v3 | kroma_v0.2_turbo_mixed_v3.safetensors | 8.67 GB |
| Mixed v4 | kroma_v0.2_turbo_mixed_v4.safetensors | 8.01 GB |
| Mixed v5 | kroma_v0.2_turbo_mixed_v5.safetensors | 7.64 GB |
Version Differences
| Version | Description |
|---|---|
| v0.1 | Kroma v0.1 LoRA merged into Krea 2 Turbo BF16, then quantized to INT8. |
| v3 | More conservative profile prioritizing quality retention. |
| v4 | Reduced model size further while maintaining similar quality. |
| v5 | Most aggressive compression profile with the smallest file size. |
Hardware Testing
Tested on:
| Component | Specification |
|---|---|
| GPU | NVIDIA GTX 1660 Super 6GB |
| RAM | 32GB |
| Runtime | ComfyUI + Comfy Kitchen |
Recommendation
- Use v0.1 if you prefer Kroma v0.1 over v0.2
- Use v4 for the best balance between size and quality.
- Use v5 if minimizing storage usage is the priority.
- Use v3 if you prefer the most conservative profile.
- Task
- Text-to-Image
- Languages
- en
- Created
- Aug 9, 2026
- Updated
- Sep 11, 2026