What GPU do I need to run samuel-vitorino/sopro-v2-turbo?

122M parameters, published in F32. View on Hugging Face

122M
Parameters
F32
Native precision
Unknown
Architecture
text-to-speech
Pipeline

sopro-v2-turbo is published by samuel-vitorino on Hugging Face, with 390 downloads and 22 likes to date. It's a unlisted-architecture model built for text-to-speech, published natively in F32.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP320.5 GB0.5 GBQuadro M40001$0.046/hr
FP8 (quantized)0.1 GB0.1 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)0.1 GB0.1 GBRTX 30701$0.088/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 sopro-v2-turbo at its published (F32) precision: 1× Quadro M4000, at $0.046/hr per GPU ($0.046/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

sopro-v2-turbo: common questions

How much VRAM does sopro-v2-turbo need?

0.5 GB at FP32, 0.1 GB at FP8 (quantized), 0.1 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 0.5 GB of weights plus inference overhead is the whole requirement.

Can sopro-v2-turbo run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 0.5 GB, or 0.5 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.2 GB, or 0.3 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.

How many copies of sopro-v2-turbo fit on one Quadro M4000?

14, by VRAM alone. That card carries 8.0 GB and one copy needs 0.5 GB at FP32, on a live rate of $0.046/hr for the whole card. Throughput is not modelled here, so 14 copies is not 14 times the requests served.

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

samuel-vitorino models

Alternatives at this size

Other models for text-to-speech within about a third of sopro-v2-turbo's 122M parameters, from other model lines.

More on sopro-v2-turbo

Related reading: H100 pricing and specs, Whisper variants compared, 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.