What GPU do I need to run Pika-Labs/Pika-H3-Flex?
33.1B parameters, published in BF16. View on Hugging Face
Set up Pika-H3-FlexPika-H3-Flex is published by Pika-Labs on Hugging Face, with 1,083 downloads and 522 likes to date. It's a unlisted-architecture model built for image-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 | 61.7 GB | 74.0 GB | RTX PRO 6000 | 1 | $1.38/hr |
| cheaper alt. | RTX 3090 | 4 | $0.647/hr | ||
| FP8 (quantized) | 30.8 GB | 37.0 GB | L40 | 1 | $0.853/hr |
| cheaper alt. | RTX 5060 Ti | 3 | $0.612/hr | ||
| INT4 (quantized) | 15.4 GB | 18.5 GB | RTX 3090 | 1 | $0.162/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 Pika-H3-Flex at its published (BF16) precision: 1× RTX PRO 6000, at $1.38/hr per GPU ($1.38/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Pika-H3-Flex: common questions
Can Pika-H3-Flex run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 74.0 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 95.0 GB RTX PRO 6000 at $1.38/hr.
What is the least VRAM Pika-H3-Flex can run in?
18.5 GB, at INT4 (quantized), which fits a 24 GB card, against 74.0 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 Pika-H3-Flex lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX PRO 6000 at $1.38/hr. At INT4 (quantized) it drops to one RTX 3090 at $0.162/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
- MiniMax-H3 (33.1B, BF16)
- P-H3-Image (33.1B, BF16)
- FastVideo-Minimax-FastH3-Preview-v0.2 (35.0B, BF16)
- FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree (35.0B, BF16)
- MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA (27.4B, BF16)
Lineage
Based on MiniMax-H3.
Alternatives at this size
Other models for image-to-video within about a third of Pika-H3-Flex's 33.1B parameters, from other model lines.
- Kandinsky-6.0-Pro-5s-Diffusers (30.1B, BF16)
More on Pika-H3-Flex
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: RTX PRO 6000 pricing and specs, Fast diffusion inference on GPU VMs, What AI inference is, and What AI model fine-tuning is.
