Granite 4.0 1b Speech
IBM · released Feb 27, 2026 · ibm-granite/granite-4.0-1b-speech
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 6
- Size
- 2.3B
Context measured in tokens
Our take
Written Sep 4, 2026Granite 4.0 is a 2.3-billion-parameter speech-to-text model from IBM with a permissive Apache licence. It is built for speed and local deployment, handling six languages and transcribing an hour of audio in about five seconds on modest hardware.
Pick this for fast local transcription on limited hardware, or for meeting-room and accented speech where it outperforms most peers. Use it if you need open-weight coverage in French, German, Spanish, Portuguese or Japanese. Skip it if your source is podcasts or internet video, where it trails the field, or if you want a fully managed hosted service rather than self-hosting.
The case for it
- Extremely fast: 661× real-time speed, turning an hour of audio into text in roughly five seconds.
- Strong on meeting audio at 7.4% word error rate, well below the field middle of 10.6%.
- Handles accented speech better than most, at 8.3% versus a field middle of 10.8%.
- Apache 2.0 licence allows commercial use, modification and redistribution.
The case against it
- Podcasts and internet video are a weak spot at 8.4% word error rate, behind the field middle of 8.2%.
- Not the leader on clean read-aloud audio: 1.1% versus the field best of 0.9%.
- No hosted providers tracked; you must run it yourself.
How good is it?
An open speech-to-text model for turning recordings of meetings and clear read-aloud speech into written text.
- transcribing recordings of meetings in a roomRecorded meetings · 14th of 92
- transcribing clear recordings of people reading aloudClean read speech · 17th of 92
TranscriptionTurning speech into text3 of 5Open ASR WER · 38th of 76
94.9%
Misses roughly one word in 20, averaged over nine English test sets.
666×43rd of 74
an hour of audio in 5 seconds, on the board's own hardware. Your machine will differ.
6
Listed on the model card. The accuracy above is English only.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case; the placing beneath each rate is against every model measured on that set.
Which languages ↓ ↑
English · French · German · Spanish · Portuguese · Japanese
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 19.9 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 27.9 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 3.1 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Granite 4.0 1b Speech loads, not how fast it transcribes. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first. This is a fit answer: whether it loads, not how fast it transcribes.
Models people weigh against Granite 4.0 1b Speech
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- ibm-granite/granite-4.0-1b-speech
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- ibm-granite-granite-4-0-1b-speech