LFM3 Models — Hardware Requirements
3 LFM3 models from Liquid AI and the community, from the smallest that runs in 2.1 GB of VRAM at Q4 up to 2.2B parameters. Every row links to full quantization tables and GPU compatibility.
All LFM3 Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| LFM3 1.7B | 1.7B | 2.1 GB | 262K | ||
| LFM3 VL 2B | 1.9B | 2.3 GB | 128K | ||
| LFM3 Omni 2B | 2.2B | 2.4 GB | 128K |
Community variants and fine-tunes(1)
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| LFM3 1.7B Base | 1.7B | 2.1 GB | 262K |
Frequently Asked Questions
- How much VRAM do I need to run a LFM3 model?
- The smallest LFM3 model, LFM3 1.7B, runs from 2.1 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 0.9 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which LFM3 models can I run on a 16 GB GPU?
- 4 of 4 LFM3 models fit in 16 GB of VRAM at Q4_K_M, including LFM3 1.7B, LFM3 VL 2B, LFM3 Omni 2B.
- What is the most popular LFM3 model to run locally?
- LFM3 1.7B is the most downloaded LFM3 model in local-friendly quantized formats. It runs from 2.1 GB of VRAM at Q4_K_M.