QuantStack / text-to-image updated 1 year ago

FLUX.1-Krea-dev-GGUF

Since this is a quantized model, all original licensing terms and usage restrictions remain in effect.

Params
Context
Downloads 30d
20 K
Likes
143
Licence: other Not gated GGUF 1 languages View on Hugging Face ↗

Download history

daily snapshots · 36 days
▲ 451 in the last 30 days (2.2%)
21 K19 K
Aug 17Aug 29Sep 10Sep 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
flux1-krea-dev-Q2_K.gguf Q2_K 4.0 GB 4.9 GB ✅ Runs comfortably
flux1-krea-dev-Q3_K_S.gguf Q3_K_S 5.2 GB 6.2 GB ✅ Runs comfortably
flux1-krea-dev-Q3_K_M.gguf Q3_K_M 5.4 GB 6.4 GB ✅ Runs comfortably
flux1-krea-dev-Q4_0.gguf Q4_0 6.8 GB 8.0 GB ✅ Runs comfortably
flux1-krea-dev-Q4_K_S.gguf Q4_K_S 6.8 GB 8.0 GB ✅ Runs comfortably
flux1-krea-dev-Q4_K_M.gguf Q4_K_M 6.9 GB 8.1 GB ✅ Runs comfortably
flux1-krea-dev-Q4_1.gguf Q4_1 7.5 GB 8.8 GB ✅ Runs comfortably
flux1-krea-dev-Q5_0.gguf Q5_0 8.3 GB 9.6 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
2025-07-31
Base model
FLUX.1-Krea-dev
Training datasets
undisclosed
Added to our catalog
2026-08-17

Family

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

Compare with any text-to-image model