whisper-large-v3-turbo-4bit
mlx-community/whisper-large-v3-turbo-4bit
Speech recognition · mlx-audio-plus
4-bit Open on Hugging Face
Parameters
807M
Weights (est.)
≈ 463 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- openai/whisper-large-v3-turbo (finetune)
- Vendor
- OpenAI · gpt-oss
- Task
- Speech recognition
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 13K in the last 30 days · 45K all time · 8 likes
- Published
- 2025-12-14 · updated 2025-12-15 (11mo ago)
- Tags
- mlx-audio-plus, whisper, speech-recognition, speech-to-text
Other MLX builds of openai/whisper-large-v3-turbo
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| whisper-large-v3-turbo-4bit (this one) | 4-bit | ≈ 463 MB | 8 GB+ | 13K |
| whisper-large-v3-turbo-8bit | 8-bit | ≈ 864 MB | 8 GB+ | 2.2K |
| whisper-large-v3-turbo-fp16 | fp16 | ≈ 1.6 GB | 8 GB+ | 332 |