MLX Community · First MLX build 24 May 2024
openchat-3.6-8b-20240522
MLX
Text llama3
A 2.3B parameter text generation model, with 3 MLX builds, from 2-bit to 8-bit.
- Parameters
- 2.3B From Hugging Face
- Quantisation
- 2-bit openchat-3.6-8b-20240522-2bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 659 MB Weights, estimated
- Downloads
- 32 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 3 GB at 2-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/openchat-3.6-8b-20240522-2bit --prompt "Hello"MLX builds
3 on mlx-community| openchat-3.6-8b-20240522-2bit | 2-bit | 659 MB | 3 GB | 32 |
|---|---|---|---|---|
| openchat-3.6-8b-20240522-4bit | 4-bit | 1.1 GB | 4 GB | 23 |
| openchat-3.6-8b-20240522-8bit | 8-bit | 2.6 GB | 5 GB | 29 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.