What GPU do I need to run MiniMaxAI/MiniMax-Music3?
2.4B parameters, published in F32. View on Hugging Face
Set up MiniMax-Music3MiniMax-Music3 is published by MiniMaxAI on Hugging Face, with 22,781 downloads and 1,322 likes to date. It's a MiniMaxMusic3ForConditionalGeneration model built for text-to-audio, 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 | 9.1 GB | 10.9 GB | V100 | 1 | $0.088/hr |
| FP8 (quantized) | 2.3 GB | 2.7 GB | RTX 4080 | 1 | $0.173/hr |
| INT4 (quantized) | 1.1 GB | 1.4 GB | RTX 3060 | 1 | $0.110/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 MiniMax-Music3 at its published (F32) precision: 1× V100, 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.
MiniMax-Music3: common questions
Does MiniMax-Music3 fit on a 12 GB GPU?
Yes. At FP32 it needs 10.9 GB of VRAM, so a 12 GB card holds it with 1.1 GB to spare. An 8 GB card is not enough for it at FP32.
Can MiniMax-Music3 run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 9.1 GB, or 10.9 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 4.5 GB, or 5.4 GB with overhead. That moves it onto a 6 GB card instead of a 12 GB one. How much accuracy the cast costs is model-specific and is not measured here.
What is the least VRAM MiniMax-Music3 can run in?
1.4 GB, at INT4 (quantized), which fits a 6 GB card, against 10.9 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.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Alternatives at this size
Other models for text-to-audio within about a third of MiniMax-Music3's 2.4B parameters, from other model lines.
- YuE2-3B (3.6B, BF16)
More on MiniMax-Music3
Fits on a 12 GB GPU at FP32: every model that fits in 12 GB.
Fits on an 8 GB GPU at FP8: every model that fits in 8 GB.
Best text-to-speech models: how MiniMax-Music3 ranks against the rest.
Related reading: V100 pricing and specs, Whisper variants compared, and What AI inference is.
