What GPU do I need to run FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2?
35.0B parameters, published in BF16. View on Hugging Face
Set up FastVideo-M…tH3-Preview-v0.2FastVideo-Minimax-FastH3-Preview-v0.2 is published by FastVideo on Hugging Face, with 1,073 downloads and 26 likes to date. It's a unlisted-architecture model built for text-to-video, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 65.3 GB | 78.3 GB | A100 | 1 | $1.21/hr |
| cheaper alt. | RTX A5000 | 4 | $0.704/hr | ||
| FP8 (quantized) | 32.6 GB | 39.2 GB | L40 | 1 | $0.742/hr |
| cheaper alt. | RTX 4000 SFF Ada | 2 | $0.396/hr | ||
| INT4 (quantized) | 16.3 GB | 19.6 GB | RTX A5000 | 1 | $0.176/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run FastVideo-Minimax-FastH3-Preview-v0.2 at its published (BF16) precision: 1× A100, at $1.21/hr per GPU ($1.21/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
FastVideo-Minimax-FastH3-Preview-v0.2: common questions
Can FastVideo-Minimax-FastH3-Preview-v0.2 run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 78.3 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 80.0 GB A100 at $1.21/hr.
What is the least VRAM FastVideo-Minimax-FastH3-Preview-v0.2 can run in?
19.6 GB, at INT4 (quantized), which fits a 24 GB card, against 78.3 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing FastVideo-Minimax-FastH3-Preview-v0.2 lower the GPU bill?
Yes. At BF16 the cheapest live fit is one A100 at $1.21/hr. At INT4 (quantized) it drops to one RTX A5000 at $0.176/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More MiniMax H3 models
- FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree (35.0B, BF16)
- MiniMax-H3 (33.1B, BF16)
Lineage
Based on MiniMax-H3.
More on FastVideo-Minimax-FastH3-Preview-v0.2
Fits on an 80 GB GPU at BF16: every model that fits in 80 GB.
Fits on a 48 GB GPU at FP8: every model that fits in 48 GB.
Fits on a 24 GB GPU at INT4: every model that fits in 24 GB.
Related reading: A100 pricing and specs, Fast diffusion inference on GPU VMs, What AI inference is, and What AI model fine-tuning is.
