Vince_AI/krea2_turbo_bf16_to_W4A4
⚡ Krea2 Turbo BF16 → W6A8 — NEW! Experimental 6-Bit Quantization | Created with VINCE W6A8 Studio A new quantized version of the original Krea 2 Turbo BF16 , converted by Vince AI using the standalone VINCE W6A8 Studio . This version introduces W6A8 quantization (6-bit weights / 8-bit activations) , offering a different balance between model size and numerical precision compared to W4A4 and W4A8. Key Features W6A8 quantization with ConvRot. 240 layers successfully quantized. Direct conversion from the original BF16 checkpoint. Clean base model — no merged LoRAs. Successfully tested with Forge
| Author / organization | Vince_AI |
|---|---|
| Downloads | 171 (as reported by Civitai) |
| Likes | 12 |
| Task | text-to-image |
| Created | 18 October 2026 |
| Last updated at source | — |
Recent changes
- 18 Oct 2026 Description: Krea2 Turbo BF16 — W4A4 W4A8 Two lightweight quantized versions of the original Krea 2 Turbo BF16 , created by Vince AI using Vince Merge Lab for Forge . Both versions are clean conversions with no merged LoRAs , designed to preserve the or → ⚡ Krea2 Turbo BF16 → W6A8 — NEW! Experimental 6-Bit Quantization | Created with VINCE W6A8 Studio A new quantized version of the original Krea 2 Turbo BF16 , converted by Vince AI using the standalone VINCE W6A8 Studio . This version introd
Changes detected by Silytics between refreshes of the source.
More from Vince_AI
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.