What GPU do I need to run darkps/ice-012-audio?

714M parameters, published in F16. View on Hugging Face

714M
Parameters
F16
Native precision
iceAudioForCausalLM
Architecture
text-to-speech
Pipeline

ice-012-audio is published by darkps on Hugging Face, with 349 downloads and 62 likes to date. It's a iceAudioForCausalLM model built for text-to-speech, published natively in F16.

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)
FP161.3 GB1.6 GBRTX 30701$0.088/hr
FP8 (quantized)0.7 GB0.8 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)0.3 GB0.4 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 ice-012-audio at its published (F16) precision: 1× RTX 3070, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

ice-012-audio: common questions

How much VRAM does ice-012-audio need?

1.6 GB at FP16, 0.8 GB at FP8 (quantized), 0.4 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 1.3 GB of weights plus inference overhead is the whole requirement.

How many copies of ice-012-audio fit on one RTX 3070?

5, by VRAM alone. That card carries 8.0 GB and one copy needs 1.6 GB at FP16, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 5 copies is not 5 times the requests served.

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

darkps models

Alternatives at this size

Other models for text-to-speech within about a third of ice-012-audio's 714M parameters, from other model lines.

More on ice-012-audio

Related reading: RTX 3070 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.