chromadb · First MLX build 31 Mar 2026
context-1
MLX
Text apache-2.0
A 21B parameter text generation model from chromadb, with 2 MLX builds, from 4-bit to 6-bit.
- Parameters
- 21B From Hugging Face
- Quantisation
- 4-bit context-1-MLX-4bit
- Memory needed
- 16 GB Estimate, unified memory
- Download
- 11.8 GB Weights, estimated
- Downloads
- 36 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 16 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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/context-1-MLX-4bit --prompt "Hello"MLX builds
2 on mlx-community| context-1-MLX-4bit | 4-bit | 11.8 GB | 16 GB | 36 |
|---|---|---|---|---|
| context-1-MLX-6bit | 6-bit | 17.0 GB | 22 GB | 31 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.