Cohere · First MLX build 5 Mar 2026
tiny-aya-fire
MLX
Text cc-by-nc-4.0
A 3.3B parameter text generation model from Cohere, with 2 MLX builds at 4-bit.
- Parameters
- 3.3B From Hugging Face
- Quantisation
- Unstated tiny-aya-fire
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.7 GB Weights, estimated
- Downloads
- 87 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 10 GB at Unstated
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/tiny-aya-fire --prompt "Hello"MLX builds
2 on mlx-community| tiny-aya-fire-4bit | 4-bit | 1.9 GB | 5 GB | 83 |
|---|---|---|---|---|
| tiny-aya-fire | Unstated | 6.7 GB | 10 GB | 87 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.