alibiserikbay · First MLX build 14 Oct 2026
JevK5
MLX
Text apache-2.0 Trending
A 4.2B parameter text generation model from alibiserikbay, with 3 MLX builds, from 4-bit to 16-bit.
- Parameters
- 4.2B From Hugging Face
- Quantisation
- 16-bit JevK5-chat-mlx-16bit
- Memory needed
- 12 GB Estimate, unified memory
- Download
- 8.4 GB Weights, estimated
- Downloads
- 463 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 12 GB at 16-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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/JevK5-chat-mlx-16bit --prompt "Hello"MLX builds
3 on mlx-community| JevK5-chat-mlx-4bit | 4-bit | 2.4 GB | 5 GB | 419 |
|---|---|---|---|---|
| JevK5-chat-mlx-8bit | 8-bit | 4.5 GB | 7 GB | 421 |
| JevK5-chat-mlx-16bit | 16-bit | 8.4 GB | 12 GB | 463 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.