LLM
GA
Open weights
LFM2-2.6B
Mobile/edge classification and assistants
Release2025-09
Context33K
Max output—
Parameters2.6B
Local / VRAM2–4 GB
LicenseOpen weights
Overview
LFM2-2.6B is a model in the LLM category from Liquid AI. It was released in 2025-09. The vendor is based in US. Best for: Mobile/edge classification and assistants.
Strengths
- Very small
- CPU-friendly
Limits
- Narrow capability
- Short context
Specifications
| Vendor | Liquid AI |
|---|---|
| Category | LLM |
| Release | 2025-09 |
| Status | GA |
| License | Open weights |
| License name | LFM Open License |
| Commercial use | Allowed |
| Parameters | 2.6B |
| Context window | 33K |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 2–4 GB |
| System RAM | 4–8 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | Medium |
| Vendor country | US |
| Vendor type | Open lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 2–4 GB. Approximate system RAM: 4–8 GB. API access is available.