Video generation
How to deploy mochi-1-preview on a GPU cloud
A 10B-parameter video generation model. Full specs, license and use cases.
mochi-1-preview size and hardware requirements
10.0B
Total parameters
Dense (no MoE)
Architecture
F32
Published precision
44.8 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 37.4 GB | 44.8 GB | RTX A6000 | 1 | $0.330/hr |
| FP8 (quantized) | 9.3 GB | 11.2 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 4.7 GB | 5.6 GB | RTX 4070 Super | 1 | $0.110/hr |
How to run mochi-1-preview
Run mochi-1-preview with Diffusers (Python)
From genmo/mochi-1-preview's own model card.
import torch
from diffusers import MochiPipeline
from diffusers.utils import export_to_video
pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview")
# Enable memory savings
pipe.enable_model_cpu_offload()
pipe.enable_vae_tiling()
prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
with torch.autocast("cuda", torch.bfloat16, cache_enabled=False):
frames = pipe(prompt, num_frames=84).frames[0]
export_to_video(frames, "mochi.mp4", fps=30)Source: https://huggingface.co/genmo/mochi-1-preview/raw/main/README.md
Run mochi-1-preview with ComfyUI
Aquanode's ComfyUI template comes with ComfyUI preinstalled. Download genmo/mochi-1-preview's checkpoint into the models folder and load it in a workflow; this is a real Aquanode template, but loading this specific checkpoint is a manual step, not a one-click deploy.
Deploy mochi-1-preview on Aquanode
Aquanode has no one-click deploy template for mochi-1-preview; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× RTX A6000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod