OpenAI · First MLX build 14 Dec 2025 · In Core AI since 8 Jun 2026
whisper-large-v3
MLXCore AI
Audio apache-2.0
A 1.5B parameter speech recognition model from OpenAI, with 3 MLX builds, from 4-bit to fp16 and Apple Core AI export recipes for iOS, macOS.
- Parameters
- 1.5B From Hugging Face
- Quantisation
- 4-bit whisper-large-v3-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 877 MB Weights, estimated
- Downloads
- 643 This build, last 30 days
- Task
- Speech recognition Audio
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 1.5B From Hugging Face
- Compression
- — Apple’s preset
- Memory needed
- — Parameter count not published
- Context
- — Fixed at export
- Precision
- — Compute precision
- Platforms
- iOS, macOS Not stated
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 8 Jun 2026 First registry commit
Memory
Will it fit?Needs about 3 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/whisper-large-v3-4bitMemory
There is no memory estimate: the parameter count for this model is not published on Hugging Face.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run models/whisper/export.py
Apple publishes the recipe, not a ready-made package: these commands convert the original weights to a Core AI .aimodel on your Mac. See the repository for requirements.
MLX builds
3 on mlx-community| whisper-large-v3-4bit | 4-bit | 877 MB | 3 GB | 643 |
|---|---|---|---|---|
| whisper-large-v3-8bit | 8-bit | 1.6 GB | 4 GB | 171 |
| whisper-large-v3-fp16 | fp16 | 3.1 GB | 6 GB | 303 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| whisper-large-v3 | iOS, macOS | — | — | — |