Granite Speech is IBM’s open-weight speech-to-text family, part of the Granite portfolio. Designed for enterprise transcription with permissive licensing.
See all models from IBMModels in family
2
Open weight
2
API only
0
Avg score
55.8
Top benchmark
—
Total HF downloads
521.2K
Primary modality
Audio
First release
Apr 2025
Latest release
Apr 2025
Every release in the Granite Speech family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB57.2 | 3B | Apr 2025 | |
| 2 | audio | CC54.4 | 9B | Apr 2025 |
When each release shipped, newest first. Useful for tracking version cadence.
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB57.2 | 3B | Apr 2025 | |
| 2 | audio | CC54.4 | 9B | Apr 2025 |
The Granite Speech family is a series of AI models from IBM. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, Granite Speech 3.3 2B is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Or Browse by Provider
See every model from a lab side by side, with aggregate stats. Useful when you want a cross-family view of one provider.
