What GPU do I need to run Edge0/Audio8-TTS-Realistic-Air?
601M parameters, published in BF16. View on Hugging Face
Audio8-TTS-Realistic-Air is published by Edge0 on Hugging Face, with 16,188 downloads and 370 likes to date. It's a ArkttsModel model built for text-to-speech, published natively in BF16.
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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 1.1 GB | 1.3 GB | RTX 3070 | 1 | $0.088/hr |
| FP8 (quantized) | 0.6 GB | 0.7 GB | RTX 4070 | 1 | $0.154/hr |
| INT4 (quantized) | 0.3 GB | 0.3 GB | RTX 3070 | 1 | $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 Audio8-TTS-Realistic-Air at its published (BF16) 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.
Audio8-TTS-Realistic-Air: common questions
How much VRAM does Audio8-TTS-Realistic-Air need?
1.3 GB at BF16, 0.7 GB at FP8 (quantized), 0.3 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 1.1 GB of weights plus inference overhead is the whole requirement.
How many copies of Audio8-TTS-Realistic-Air fit on one RTX 3070?
5, by VRAM alone. That card carries 8.0 GB and one copy needs 1.3 GB at BF16, 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.
More Edge0 models
- Audio8-ASR-Infinite (4.1B, BF16)
Alternatives at this size
Other models for text-to-speech within about a third of Audio8-TTS-Realistic-Air's 601M parameters, from other model lines.
- parler-tts-mini-v1 (878M, F32)
- ice-012-audio (714M, F16)
- OmniVoice (613M, F32)
More on Audio8-TTS-Realistic-Air
Fits on an 8 GB GPU at BF16: every model that fits in 8 GB.
Best text-to-speech models: how Audio8-TTS-Realistic-Air ranks against the rest.
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