vantagewithai / text-to-image updated 2 months ago

Krea-2-Turbo-GGUF

See our collection of in-house trained LoRAs trained on Raw and meant to be used with Turbo: Krea-2 LoRA Collection

Params
Context
Downloads 30d
60 K
Likes
154
Licence: other Not gated GGUF 1 languages View on Hugging Face ↗

Download history

daily snapshots · 56 days
▲ 13 K in the last 30 days (26.9%)
73 K37 K
Jul 28Aug 15Sep 3Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
krea2_turbo-Q2_K.gguf Q2_K 4.9 GB 5.9 GB ✅ Runs comfortably
krea2_turbo-Q3_K_M.gguf Q3_K_M 6.0 GB 7.1 GB ✅ Runs comfortably
krea2_turbo-Q3_K_S.gguf Q3_K_S 6.0 GB 7.1 GB ✅ Runs comfortably
krea2_turbo-Q4_0.gguf Q4_0 7.5 GB 8.7 GB ✅ Runs comfortably
krea2_turbo-Q4_K_M.gguf Q4_K_M 7.5 GB 8.7 GB ✅ Runs comfortably
krea2_turbo-Q4_K_S.gguf Q4_K_S 7.5 GB 8.7 GB ✅ Runs comfortably
krea2_turbo-Q4_1.gguf Q4_1 8.2 GB 9.5 GB ✅ Runs comfortably
krea2_turbo-Q5_0.gguf Q5_0 8.9 GB 10.3 GB ✅ Runs comfortably
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
2026-06-23
Base model
Krea-2-Turbo
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-to-image model