TheDrummer · First MLX build 8 Jun 2025
Big-Alice-28B-v1
MLX
Text mit
A 29B parameter text generation model from TheDrummer, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 29B From Hugging Face
- Quantisation
- bf16 Big-Alice-28B-v1-bf16
- Memory needed
- 66 GB Estimate, unified memory
- Download
- 57.2 GB Weights, estimated
- Downloads
- 33 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 66 GB at bf16
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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Big-Alice-28B-v1-bf16 --prompt "Hello"MLX builds
4 on mlx-community| Big-Alice-28B-v1-4bit | 4-bit | 16.1 GB | 20 GB | 27 |
|---|---|---|---|---|
| Big-Alice-28B-v1-6bit | 6-bit | 23.2 GB | 28 GB | 23 |
| Big-Alice-28B-v1-8bit | 8-bit | 30.4 GB | 36 GB | 19 |
| Big-Alice-28B-v1-bf16 | bf16 | 57.2 GB | 66 GB | 33 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.