Model reference · open weights

BackMixes

Image xFutureTechx Text→image 1 build Open weights 9k dl/mo

BackMixes is an open-weight image model from xFutureTechx. BackMixes (BF16) weighs 284 GB; the smallest configuration that runs it is RTX 4060 Ti 16 GB.

What it is

Released byxFutureTechx
Released2023-11-25
VRAM284 GB for the weights

What it runs on

Memory and cards for BackMixes (BF16)

284 GBweights, file size
6.9 GBbiggest part
5.0 GBworking memory, one 1024² image
537 MBruntime overhead
CardOne imageMemory
RTX 3060 12 GBdoes not fit11.6 GB
RTX 4060 Ti 16 GBfits (encoders offloaded)15.4 GB
RTX 3090 24 GBfits (encoders offloaded)23.4 GB
RTX 4090 24 GBfits (encoders offloaded)23.4 GB
RTX 5090 32 GBfits (encoders offloaded)31.0 GB
L40S 48 GBfits (encoders offloaded)44.0 GB
A100 80 GBfits (encoders offloaded)78.2 GB
H100 80 GBfits (encoders offloaded)78.1 GB
RTX PRO 6000 Blackwell 96 GBfits (encoders offloaded)93.8 GB
DGX Spark (GB10) 128 GB unifiedfits (encoders offloaded)107 GB
H200 141 GBfits (encoders offloaded)138 GB
B200 180 GBfits (encoders offloaded)176 GB

From the model card

What xFutureTechx says about BackMixes

We've long since retired from AI, but if you find our content useful even long after please feel free to send us a KoFI Otherwise feel free to partake in our affiliate links

Membership / Ko-Fi

Runpod

VastAI

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Running it yourself

Run it on a rented GPU

Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel: its default workflow loads a checkpoint. Choose this model's file in Load Checkpoint, with the settings its model card gives.

# 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 model (2.0 GB)
get xFutureTechx/BackMixes BigFizz2pt3.fp16.safetensors checkpoints

start-comfyui
Renting a GPU: connect, tunnels, 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
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms