OpenModelsHQ

whisper-large-v3-LoS-punctuated

Barcelona Supercomputing CenterSpeechDenseApache-2.0

whisper-large-v3-LoS-punctuated is an open-weight speech to text model from Barcelona Supercomputing Center. We do not have a parameter count yet, so there is no memory estimate.

Overview

Estimated memory at 4-bit
Unknown

We do not have a parameter count for this model yet, so we cannot estimate its memory.

Total parameters
Unknown
Dense
Type
Speech to text
Released 16 Dec 2025
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Barcelona Supercomputing Center
Released
16 Dec 2025
Parameters
Unknown
Type
Speech to text
License
Apache-2.0
HF downloads, 30 days
220
View all

Will it run on your hardware?

How we estimate
FormatMemory neededExample hardware
4-bit (Q4)UnknownNo estimate without a parameter count
8-bit (Q8)UnknownNo estimate without a parameter count
16-bit (BF16)UnknownNo estimate without a parameter count

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

No trusted GGUF build found yet.

Find compatible hardware

Through an API

No hosted API found.

More about this model

Frequently asked questions

How much memory does whisper-large-v3-LoS-punctuated need? We cannot estimate it yet, because we do not have a parameter count for this model.

Can I run whisper-large-v3-LoS-punctuated on a Mac? We cannot say yet, because we do not have a parameter count for this model.

What does it need to run? We cannot say yet, because we do not have a parameter count for this model. Estimated memory for the weights at 4-bit (plus runtime overhead). Image, video and speech models also need working memory that depends on resolution or clip length.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card.