5-bit Open on Hugging Face
Parameters
742M
Weights (est.)
≈ 511 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/LFM2-700M-5bit --prompt "Hello"
Details
- Base model
- LiquidAI/LFM2-700M (quantized)
- Vendor
- LiquidAI
- Task
- Text generation
- Quantisation
- 5-bit
- Licence
- lfm1.0
- Downloads
- 32 in the last 30 days · 197 all time · 1 likes
- Published
- 2025-07-11 · updated 2025-07-11 (1y ago)
- Languages
- en, ar, zh, fr, de, ja, ko, es
- Tags
- lfm2, liquid, edge
Other MLX builds of LiquidAI/LFM2-700M
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LFM2-700M-4bit | 4-bit | ≈ 418 MB | 8 GB+ | 131 |
| LFM2-700M-5bit (this one) | 5-bit | ≈ 511 MB | 8 GB+ | 32 |
| LFM2-700M-6bit | 6-bit | ≈ 603 MB | 8 GB+ | 41 |
| LFM2-700M-8bit | 8-bit | ≈ 789 MB | 8 GB+ | 93 |
| LFM2-700M-bf16 | bf16 | ≈ 1.5 GB | 8 GB+ | 34 |