MLX Community · First MLX build 9 Apr 2025
3b-fr-pretrain-research_release
MLX
Audio llama3.2
A 3.3B parameter text to speech model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 3.3B From Hugging Face
- Quantisation
- 4-bit 3b-fr-pretrain-research_release-4bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 1.9 GB Weights, estimated
- Downloads
- 93 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 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/3b-fr-pretrain-research_release-4bitMLX builds
4 on mlx-community| 3b-fr-pretrain-research_release-4bit | 4-bit | 1.9 GB | 5 GB | 93 |
|---|---|---|---|---|
| 3b-fr-pretrain-research_release-6bit | 6-bit | 2.7 GB | 5 GB | 91 |
| 3b-fr-pretrain-research_release-8bit | 8-bit | 3.5 GB | 6 GB | 49 |
| 3b-fr-pretrain-research_release-bf16 | bf16 | — | — | 42 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.