Flux-2-Dev
📂 ComfyUI/ ├── 📂 models/ │ ├── 📂 diffusionmodels/ │ │ └── flux2devfp8mixed.safetensors │ ├── 📂 loras/ │ │ ├── Flux2TurboComfyv2.safetensors │ │ └── Flux2-Turbo-LoRAcomfyui.safetensors │ ├── 📂 textencoders/ │ │ ├── mistral3smallflux2bf16.safetensors │ │ ├── mistral3smallflux2fp4mixed.safetensors │ │ └── mistral3smallflux2fp8.safetensors │ ├── 📂 vae/ │ │ └── flux2-vae.safetensors
Params
—
Context
—
Downloads 30d
998 K
Likes
372
Download history
daily snapshots · 14 days1.1 M998 K
Oct 28Nov 1Nov 6Nov 10
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 | 107.2 GB | 118.4 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
- 2025-11-25
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-28
Compare with any text-to-image model