bf16 Open on Hugging Face
Parameters
354M
Weights (est.)
≈ 709 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/LFM2-350M-bf16 --prompt "Hello"
Details
- Base model
- LiquidAI/LFM2-350M (finetune)
- Vendor
- LiquidAI
- Task
- Text generation
- Quantisation
- bf16
- Licence
- lfm1.0
- Downloads
- 27 in the last 30 days · 248 all time · 2 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/LFM2-350M
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LFM2-350M-4bit | 4-bit | ≈ 199 MB | 8 GB+ | 184 |
| LFM2-350M-5bit | 5-bit | ≈ 244 MB | 8 GB+ | 24 |
| LFM2-350M-6bit | 6-bit | ≈ 288 MB | 8 GB+ | 34 |
| LFM2-350M-8bit | 8-bit | ≈ 377 MB | 8 GB+ | 529 |
| LFM2-350M-MLX | — | ≈ 709 MB | 8 GB+ | 59 |
| LFM2-350M-bf16 (this one) | bf16 | ≈ 709 MB | 8 GB+ | 27 |