4-bit Open on Hugging Face
Parameters
9.0B
Weights (est.)
≈ 5.1 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/K2-Horizon-7B-4bit --prompt "Hello"
Details
- Base model
- IFM/K2-Horizon-7B (quantized)
- Vendor
- IFM
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 555 in the last 30 days · 952 all time · 1 likes
- Published
- 2026-09-29 · updated 2026-09-30 (1mo ago)
- Tags
- k2_horizon, quantized, dense, k2-horizon
Other MLX builds of IFM/K2-Horizon-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| K2-Horizon-7B-4bit (this one) | 4-bit | ≈ 5.1 GB | 8 GB+ | 555 |
| K2-Horizon-7B-oQ6e | 6-bit | ≈ 7.3 GB | 16 GB+ | 816 |
| K2-Horizon-7B-8bit | 8-bit | ≈ 9.6 GB | 16 GB+ | 148 |
| K2-Horizon-7B-chat-mlx-16bit | 16-bit | ≈ 18.0 GB | 24 GB+ | 361 |
| K2-Horizon-7B-bf16 | bf16 | ≈ 18.0 GB | 24 GB+ | 99 |