Sign In
homemodelsimagesvideos3D Modelshubsarticlescomicscruciblesupdatesshop

Anima Turbo - Less VRAM & Fast! (MXFP8)

750

Updated: Oct 5, 2026

base model

Loaded

Download

1 variant available

mxfp8 SafeTensor

anima_turbov11_mxfp8.safetensors

Block-scaled 8-bit, near-FP16 quality • 2.15 GB

Verified:

Type
Checkpoint Trained
Stats

215

750

932

Generation

Loaded

Reviews

(23)

Published

Oct 4, 2026

Base Model

Anima

Hash
AutoV2
5BE978541B
default creator card background decoration
Base Model Creators position #52

#52

Reactions - 416

416

Followers - 25

25

Downloads - 1421

1.4K

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

ComfyUI_temp_rqtui_00097_.png

This is a highly optimized, mixed-precision (MXFP8) quantized version of the Anima Turbo V1.0 model. It was created to provide a much lighter and faster generation experience without noticeably sacrificing visual fidelity.

If you are running on a GPU with limited VRAM, or if you want to free up memory to run heavier ComfyUI workflows (like multiple ControlNets, upscale pipelines, or LoRAs), this checkpoint is for you.