4-bit Open on Hugging Face
Parameters
1.2B
Weights (est.)
≈ 659 MB
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/LFM2.5-1.2B-Instruct-OptiQ-4bit --prompt "Hello"
Details
- Base model
- LiquidAI/LFM2.5-1.2B-Instruct (quantized)
- Vendor
- LiquidAI
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- lfm1.0
- Downloads
- 206 in the last 30 days · 662 all time · 0 likes
- Published
- 2026-08-05 · updated 2026-10-14 (27d ago)
- Tags
- lfm2, optiq, quantized, 4bit, mixed-precision, liquid-ai, apple-silicon, on-device
Other MLX builds of LiquidAI/LFM2.5-1.2B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LFM2.5-1.2B-Instruct-4bit | 4-bit | ≈ 659 MB | 8 GB+ | 5.5K |
| LFM2.5-1.2B-Instruct-OptiQ-4bit (this one) | 4-bit | ≈ 659 MB | 8 GB+ | 206 |
| LFM2.5-1.2B-Instruct-5bit | 5-bit | ≈ 805 MB | 8 GB+ | 31 |
| LFM2.5-1.2B-Instruct-6bit | 6-bit | ≈ 951 MB | 8 GB+ | 42 |
| LFM2.5-1.2B-Instruct-8bit | 8-bit | ≈ 1.2 GB | 8 GB+ | 91 |
| LFM2.5-1.2B-Instruct-bf16 | bf16 | ≈ 2.3 GB | 8 GB+ | 58 |