What GPU do I need to run Aratako/Irodori-TTS-v4-Large?
3.3B parameters, published in F32. View on Hugging Face
Irodori-TTS-v4-Large is published by Aratako on Hugging Face, with 0 downloads and 64 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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 12.2 GB | 14.7 GB | V100 | 1 | $0.110/hr |
| cheaper alt. | Quadro M4000 | 2 | $0.092/hr | ||
| FP8 (quantized) | 3.1 GB | 3.7 GB | RTX 5060 Ti | 1 | $0.145/hr |
| INT4 (quantized) | 1.5 GB | 1.8 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 Irodori-TTS-v4-Large at its published (F32) precision: 1× V100, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Irodori-TTS-v4-Large: common questions
Does Irodori-TTS-v4-Large fit on a 16 GB GPU?
Yes. At FP32 it needs 14.7 GB of VRAM, so a 16 GB card holds it with 1.3 GB to spare. A 12 GB card is not enough for it at FP32.
Can Irodori-TTS-v4-Large run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 12.2 GB, or 14.7 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 6.1 GB, or 7.3 GB with overhead. That moves it onto an 8 GB card instead of a 16 GB one. How much accuracy the cast costs is model-specific and is not measured here.
What is the least VRAM Irodori-TTS-v4-Large can run in?
1.8 GB, at INT4 (quantized), which fits a 6 GB card, against 14.7 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 Irodori-TTS-v4-Large lower the GPU bill?
Yes. At FP32 the cheapest live fit is one V100 at $0.110/hr. At INT4 (quantized) it drops to one RTX 3070 at $0.088/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Alternatives at this size
Other models for text-to-speech within about a third of Irodori-TTS-v4-Large's 3.3B parameters, from other model lines.
- VoxCPM2 (2.3B, BF16)
- s2-pro (4.6B, BF16)
- higgs-tts-3-4b (4.7B, BF16)
- VibeVoice-1.5B (2.7B, BF16)
- Veena (3.8B, BF16)
More on Irodori-TTS-v4-Large
Fits on a 16 GB GPU at FP32: every model that fits in 16 GB.
Fits on an 8 GB GPU at FP8: every model that fits in 8 GB.
Best text-to-speech models: how Irodori-TTS-v4-Large ranks against the rest.
Related reading: V100 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