LLM
GA
Open weights
LFM2-24B
High throughput on CPU/edge devices
Release2026-01
Context131K
Max output—
Parameters24B
Local / VRAM16–24 GB
LicenseOpen weights
Overview
LFM2-24B is a model in the LLM category from Liquid AI. It was released in 2026-01. The vendor is based in US. Best for: High throughput on CPU/edge devices.
Strengths
- Fast on CPU
- Small memory footprint
- Long context
Limits
- No vision
- Not frontier reasoning
Specifications
| Vendor | Liquid AI |
|---|---|
| Category | LLM |
| Release | 2026-01 |
| Status | GA |
| License | Open weights |
| License name | LFM Open License |
| Commercial use | Allowed |
| Parameters | 24B |
| Architecture | hybrid conv-SSM |
| Context window | 131K |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 16–24 GB |
| System RAM | 32–64 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: 16–24 GB. Approximate system RAM: 32–64 GB. API access is available.