5-bit Open on Hugging Face
Parameters
1.2B
Weights (est.)
≈ 805 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-JP-5bit --prompt "Hello"
Details
- Base model
- LiquidAI/LFM2.5-1.2B-JP (quantized)
- Vendor
- LiquidAI
- Task
- Text generation
- Quantisation
- 5-bit
- Licence
- lfm1.0
- Downloads
- 20 in the last 30 days · 147 all time · 0 likes
- Published
- 2026-01-06 · updated 2026-01-06 (10mo ago)
- Languages
- en, ja
- Tags
- lfm2, liquid, lfm2.5, edge
Other MLX builds of LiquidAI/LFM2.5-1.2B-JP
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LFM2.5-1.2B-JP-4bit | 4-bit | ≈ 659 MB | 8 GB+ | 52 |
| LFM2.5-1.2B-JP-5bit (this one) | 5-bit | ≈ 805 MB | 8 GB+ | 20 |
| LFM2.5-1.2B-JP-6bit | 6-bit | ≈ 951 MB | 8 GB+ | 17 |
| LFM2.5-1.2B-JP-8bit | 8-bit | ≈ 1.2 GB | 8 GB+ | 21 |
| LFM2.5-1.2B-JP-bf16 | bf16 | ≈ 2.3 GB | 8 GB+ | 23 |