Mamba-24M (SC09)

Closed weights Carnegie Mellon University (CMU),Princeton University 23.4M parameters December 2023

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Carnegie Mellon University (CMU),Princeton University
Organisation type
Academia,Academia
Country
United States of America
Published
1 December 2023
Authors
Albert Gu, Tri Dao

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Speech
Task
Audio generation, Speech synthesis, Text-to-speech (TTS)

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
23.4M

Table 4

Training data
96,672 tokens

Section 4.4.2: "We largely follow the autoregressive training setup and generation protocol of Goel et al. (2022)" In which they model raw audio waveforms, such that each sample is a datapoint. SC09 is 5.3 hours long. 5.3h * 3600 sec/h * 16k samples/sec = 305,280,000 samples Appendix E.4.2: "We used a learning rate of 0.002 and 200000 training steps at a batch size of 16... training went through 100 epochs"

Epochs
100

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

no code or weights for 24M Mamaba model, but there are code and weights for other Mamba models: https://github.com/state-spaces/mamba

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
SOTA improvement

"SC09 is a benchmark speech generation dataset (Donahue, McAuley, and Puckette 2019; Warden 2018), consisting of 1-second clips sampled at 16000 Hz of the digits “zero” through “nine” with highly variable characteristics. We largely follow the autoregressive training setup and generation protocol of Goel et al. (2022). Table 4 shows automated metrics of the Mamba-UNet model compared to a variety of baselines from Goel et al. (2022): WaveNet (Oord et al. 2016), SampleRNN (Mehri et al. 2017), Wav…

Record confidence
Confident
Citations
7,063

Sources

Where this record came from and when it was last checked.

Reference
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Last updated
25 May 2026

What the numbers mean

What this model is

Mamba-24M (SC09) was published by Carnegie Mellon University (CMU),Princeton University, in United States of America, in December 2023. The organisation is categorised as academia,Academia.

It works in Speech, and is recorded as doing audio generation, Speech synthesis, Text-to-speech (TTS).

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

It was trained on about 96,672 tokens of text.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

Mamba-24M (SC09) — common questions

01

When was Mamba-24M (SC09) released?

Mamba-24M (SC09) was published in December 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

What is Mamba-24M (SC09) used for?

Mamba-24M (SC09) works in Speech, and is recorded as handling audio generation, Speech synthesis, Text-to-speech (TTS). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

What GPU do I need to run Mamba-24M (SC09)?

None. Mamba-24M (SC09) is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

04

Is Mamba-24M (SC09) open source?

No. Mamba-24M (SC09) has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does Mamba-24M (SC09) have?

Mamba-24M (SC09) has 23.4M parameters. Table 4. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

06

Who created Mamba-24M (SC09)?

Mamba-24M (SC09) was published by Carnegie Mellon University (CMU),Princeton University, based in United States of America, categorised as academia,Academia.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.