Model reference · open weights
kb-whisper-coreml is an open-weight audio or speech model from mickekringai. Built for Apple devices (Core ML). It does not run on NVIDIA GPUs.
Summary of the mickekringai/kb-whisper-coreml model card, 2026-10-01
What it is
| Released by | mickekringai |
|---|---|
| Released | 2025-09-15 |
| VRAM | 5.2 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This repository contains the conversion of KBLab/kb-whisper models to the CoreLM format for use with WhisperKit in MacOS and iOS applications.
The original models were converted using WhisperKitTools from https://github.com/argmaxinc/whisperkittools
September 15, 2025 Micke Kring
For more information about the original model, see its model cards.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works
Running it
Built for Apple devices (Core ML). It does not run on NVIDIA GPUs.