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-Thinking-4bit --prompt "Hello"
Details
- Base model
- LiquidAI/LFM2.5-1.2B-Thinking (quantized)
- Vendor
- LiquidAI
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- lfm1.0
- Downloads
- 199 in the last 30 days · 1.4K all time · 0 likes
- Published
- 2026-01-20 · updated 2026-08-13 (3mo ago)
- Languages
- en, ar, zh, fr, de, ja, ko, es
- Tags
- lfm2, liquid, lfm2.5, edge
Other MLX builds of LiquidAI/LFM2.5-1.2B-Thinking
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LFM2.5-1.2B-Thinking-OptiQ-4bit | 4-bit | ≈ 659 MB | 8 GB+ | 304 |
| LFM2.5-1.2B-Thinking-4bit (this one) | 4-bit | ≈ 659 MB | 8 GB+ | 199 |
| LFM2.5-1.2B-Thinking-5bit | 5-bit | ≈ 805 MB | 8 GB+ | 31 |
| LFM2.5-1.2B-Thinking-6bit | 6-bit | ≈ 951 MB | 8 GB+ | 690 |
| LFM2.5-1.2B-Thinking-8bit | 8-bit | ≈ 1.2 GB | 8 GB+ | 47 |
| LFM2.5-1.2B-Thinking-bf16 | bf16 | ≈ 2.3 GB | 8 GB+ | 40 |