IFM · First MLX build 29 Sept 2026
K2-Horizon-0.9B
MLX
Text apache-2.0
A 1.1B parameter text generation model from IFM, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 1.1B From Hugging Face
- Quantisation
- 16-bit K2-Horizon-0.9B-chat-mlx-16bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.2 GB Weights, estimated
- Downloads
- 291 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 5 GB at 16-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/K2-Horizon-0.9B-chat-mlx-16bit --prompt "Hello"MLX builds
4 on mlx-community| K2-Horizon-0.9B-4bit | 4-bit | 607 MB | 3 GB | 91 |
|---|---|---|---|---|
| K2-Horizon-0.9B-8bit | 8-bit | 1.1 GB | 4 GB | 116 |
| K2-Horizon-0.9B-chat-mlx-16bit | 16-bit | 2.2 GB | 5 GB | 291 |
| K2-Horizon-0.9B-bf16 | bf16 | 2.2 GB | 5 GB | 76 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.