6-bit Open on Hugging Face
Parameters
354M
Weights (est.)
≈ 288 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/LFM2.5-350M-6bit --prompt "Hello"
Details
- Base model
- LiquidAI/LFM2.5-350M (quantized)
- Vendor
- LiquidAI
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- lfm1.0
- Downloads
- 57 in the last 30 days · 1.2K all time · 0 likes
- Published
- 2026-03-31 · updated 2026-08-13 (3mo ago)
- Languages
- en, ar, zh, fr, de, ja, ko, es, pt
- Tags
- lfm2, liquid, lfm2.5, edge
Other MLX builds of LiquidAI/LFM2.5-350M
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LFM2.5-350M-OptiQ-4bit | 4-bit | ≈ 199 MB | 8 GB+ | 205 |
| LFM2.5-350M-6bit (this one) | 6-bit | ≈ 288 MB | 8 GB+ | 57 |
| LFM2.5-350M-8bit | 8-bit | ≈ 377 MB | 8 GB+ | 61 |
| LFM2.5-350M-bf16 | bf16 | ≈ 709 MB | 8 GB+ | 41 |