What GPU do I need to run ai4bharat/indic-parler-tts?
938M parameters, published in F32. View on Hugging FaceGated
Set up indic-parler-ttsindic-parler-tts is published by ai4bharat on Hugging Face, with 355,610 downloads and 313 likes to date. It's a ParlerTTSForConditionalGeneration model built for text-to-speech, published natively in F32, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
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 indic-parler-tts at its published (F32) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
indic-parler-tts: common questions
How much VRAM does indic-parler-tts need?
4.2 GB at FP32, 1.0 GB at FP8 (quantized), 0.5 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 3.5 GB of weights plus inference overhead is the whole requirement.
Do I need approval to download indic-parler-tts?
Yes. ai4bharat gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 4.2 GB the model needs once you have them.
Can indic-parler-tts run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 3.5 GB, or 4.2 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 1.7 GB, or 2.1 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More ai4bharat models
- bert-base-uncased (110M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
- Qwen3.5-9B (9.7B, BF16)
