kakaocorp · First MLX build 4 Aug 2026
kanana-2-3b-instruct
MLX
Text kanana-open-license
A 3.2B parameter text generation model from kakaocorp, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 3.2B From Hugging Face
- Quantisation
- 4-bit kanana-2-3b-instruct-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.8 GB Weights, estimated
- Downloads
- 164 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 4 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/kanana-2-3b-instruct-4bit --prompt "Hello"MLX builds
4 on mlx-community| kanana-2-3b-instruct-4bit | 4-bit | 1.8 GB | 4 GB | 164 |
|---|---|---|---|---|
| kanana-2-3b-instruct-mixed_4_6 | 4-bit | 1.8 GB | 4 GB | 34 |
| kanana-2-3b-instruct-6bit | 6-bit | 2.6 GB | 5 GB | 35 |
| kanana-2-3b-instruct-8bit | 8-bit | 3.4 GB | 6 GB | 68 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.