katanemo · First MLX build 17 Oct 2025
Arch-Router-1.5B
MLX
Text katanemo-research
A 1.5B parameter text generation model from katanemo, with one MLX build at 8-bit.
- Parameters
- 1.5B From Hugging Face
- Quantisation
- 8-bit Arch-Router-1.5B-mlx-8Bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.6 GB Weights, estimated
- Downloads
- 1.2K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 8-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/Arch-Router-1.5B-mlx-8Bit --prompt "Hello"MLX builds
1 on mlx-community| Arch-Router-1.5B-mlx-8Bit | 8-bit | 1.6 GB | 4 GB | 1.2K |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.