AI Index

Granite Speech 5.0 2B

Speech to text IBM Partly verified
  • Open weights

Prices

0 offerings · prices as listed

No priced offering is listed for this model yet.

Run locally

Weights: ibm-granite/granite-speech-5.0-2b
  • Parameters 2.3B
  • Dense
  • Native precision BF16
  • Layers 40
  • KV cache per token 80 KB
  • Config positions 16K (config.json max_position_embeddings)
My hardware GeForce RTX 4090 24 GB · 1008 GB/s · 64 GB DDR5 dual channel · 89.6 GB/s

Memory isn’t estimated for this type: it depends on resolution, length and pipeline. Its weights:

PrecisionWeights
BF16 (native)maker’s file4.7 GB
Q8_0maker’s file1.8 GB
Q6_Kmaker’s file1.4 GB
Q5_K_Mmaker’s file1.2 GB
Q5_0maker’s file1.2 GB
Q4_K_Mmaker’s file1.1 GB
Q4_0maker’s file1.0 GB
Q3_K_Mmaker’s file0.9 GB
Q2_Kmaker’s file0.7 GB

Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated

Cited scores

From third-party leaderboards, not measured by us

No cited leaderboard covers speech recognition yet. We will cite one when its license allows.

Changes

All changes →
  1. New speech to text model

Sources

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

IBM · United States · ibm.com