Model reference · open weights
FLUX.2-dev is an open-weight image model from Black Forest Labs. FLUX.2-dev-NVFP4 (NVFP4) weighs 43.8 GB; the smallest configuration that runs it is RTX 5090 32 GB.
Summary of the black-forest-labs/FLUX.2-dev model card, 2026-10-01. The estimate below is for another build of the family.
What it is
| Released by | Black Forest Labs |
|---|---|
| Released | 2025-11-22 |
| Parameters | 32.2B |
| VRAM | 43.8 GB for the weights |
What it runs on
| Card | One image | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4090 24 GB | does not fit | |
| RTX 5090 32 GB | tight (encoders offloaded) | 31.0 GB |
| L40S 48 GB | fits (encoders offloaded) | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
Builds
| Build | Params | Precision | Weights | Smallest setup |
|---|---|---|---|---|
| FLUX.2-dev ↗ | 32.2B | BF16 | 113 GB | H100 80 GB |
| FLUX.2-dev-NVFP4 (above) ↗ | — | NVFP4 | 43.8 GB | RTX 5090 32 GB |
| FLUX.2-dev-GGUF ↗ packaged by unsloth 16 builds: Q2_K 12.9 GB … F16 64.4 GB the transformer alone, to use with the text encoders and VAE |
— | GGUF | 20.0 GB | RTX 5090 32 GB |
| FLUX.2-dev ↗ packaged by unsloth |
32.2B | BF16 | 113 GB | H100 80 GB |
From the model card
FLUX.2 [dev] is a 32 billion parameter rectified flow transformer capable of generating, editing and combining images based on text instructions.
For more information, please read our blog post.
This repository holds an NVFP4 version and a mixed NVFP4/BF16 version of FLUX.2 [dev]. The mixed version has a small set of weights in BF16. The main repository of this model (full BF16 weights) can be found here.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → Flux.2 Dev: it loads ComfyUI's own build of this model, the files above.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the files of the template “Flux.2 Dev” (69.0 GB)
get black-forest-labs/FLUX.2-small-decoder full_encoder_small_decoder.safetensors vae
get Comfy-Org/flux2-dev split_files/text_encoders/mistral_3_small_flux2_bf16.safetensors text_encoders
get ByteZSzn/Flux.2-Turbo-ComfyUI Flux_2-Turbo-LoRA_comfyui.safetensors loras
get Comfy-Org/flux2-dev split_files/diffusion_models/flux2_dev_fp8mixed.safetensors diffusion_models
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT