What GPU do I need to run robbyant/lingbot-world-fast?

18.5B parameters, published in F32. View on Hugging Face

18.5B
Parameters
F32
Native precision
Unknown
Architecture
image-to-video
Pipeline

lingbot-world-fast is published by robbyant on Hugging Face, with 10,892 downloads and 22 likes to date. It's a unlisted-architecture model built for image-to-video, published natively in F32.

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.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP3269.1 GB82.9 GBRTX PRO 60001$1.38/hr
cheaper alt.P404$0.647/hr
FP8 (quantized)17.3 GB20.7 GBRTX 40901$0.374/hr
cheaper alt.RTX 5060 Ti2$0.361/hr
INT4 (quantized)8.6 GB10.4 GBRTX 30601$0.110/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 lingbot-world-fast at its published (F32) 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.

lingbot-world-fast: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Multi-head attention: every layer caches keys and values for every head. Cached per token: 819,200 bytes at 16-bit.

The model's maximum context length is not published in its configuration, so no per-context figures are shown.

Computed from the layer, head and window counts in the model's own configuration (robbyant/lingbot-world-fast), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

lingbot-world-fast: common questions

Can lingbot-world-fast run on a single GPU?

Yes, but not on a desktop card. At FP32 it needs 82.9 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.

Can lingbot-world-fast run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 69.1 GB, or 82.9 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 34.5 GB, or 41.4 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.

What is the least VRAM lingbot-world-fast can run in?

10.4 GB, at INT4 (quantized), which fits a 12 GB card, against 82.9 GB at FP32. 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 lingbot-world-fast lower the GPU bill?

Yes. At FP32 the cheapest live fit is one RTX PRO 6000 at $1.38/hr. At INT4 (quantized) it drops to one RTX 3060 at $0.110/hr, provided a quantized checkpoint exists for it.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

robbyant models

Alternatives at this size

Other models for image-to-video within about a third of lingbot-world-fast's 18.5B parameters, from other model lines.

More on lingbot-world-fast

Related reading: RTX PRO 6000 pricing and specs, Fast diffusion inference on GPU VMs, and What AI inference is.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.