MLX Community · First MLX build 9 Jul 2024
calm3-22b-chat
MLX
apache-2.0
A 23B parameter model, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 23B From Hugging Face
- Quantisation
- 4-bit calm3-22b-chat-4bit
- Memory needed
- 17 GB Estimate, unified memory
- Download
- 12.7 GB Weights, estimated
- Downloads
- 30 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 17 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/calm3-22b-chat-4bitMLX builds
3 on mlx-community| calm3-22b-chat-4bit | 4-bit | 12.7 GB | 17 GB | 30 |
|---|---|---|---|---|
| calm3-22b-chat-8bit | 8-bit | 24.0 GB | 29 GB | 30 |
| calm3-22b-chat | Unstated | 45.1 GB | 53 GB | 24 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.