Model Library
Liquid AIReleased January 20, 2026LFM2.5-1.2B-Thinking
Liquid AI · Released January 20, 2026
Intelligence score
3
At a glance
- Intelligence
- 3
- Speed
- —
- Latency
- —
- Input price
- Not published
- Output price
- Not published
- Context window
- 32Ktokens
- Parameters
- 1.17billions
Summary
Comparison summary
LFM2.5-1.2B-Thinking scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 4).
Specifications
Technical specifications
| Model name | LFM2.5-1.2B-Thinking |
|---|---|
| Provider | Liquid AI |
| Release date | January 20, 2026 |
| Intelligence score | 3 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | Not published |
| Output price | Not published |
| Context window | 32,000 tokens |
| Parameters | 1.17B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | lfm 1 |
| API availability | — |
| Source | Model Intelligence legacy profile: lfm2-5-1-2b-thinking |
FAQ · 15
Frequently asked questions
LFM2.5-1.2B-Thinking was released on January 20, 2026.
LFM2.5-1.2B-Thinking was created by Liquid AI.
LFM2.5-1.2B-Thinking scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 4).
Yes, LFM2.5-1.2B-Thinking is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
LFM2.5-1.2B-Thinking supports text input.
LFM2.5-1.2B-Thinking supports text output.
No, LFM2.5-1.2B-Thinking does not support image input. It can only process text.
No, LFM2.5-1.2B-Thinking is not multimodal. It only supports text input.
LFM2.5-1.2B-Thinking has a context window of 32k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, LFM2.5-1.2B-Thinking is open weights. The model weights are publicly available and can be downloaded for self-hosting.
LFM2.5-1.2B-Thinking has 1.17 billion parameters.
LFM2.5-1.2B-Thinking is released under the lfm 1.0 license. This license allows commercial use.
LFM2.5-1.2B-Thinking achieves a score of 3 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
LFM2.5-1.2B-Thinking is an open weights model that can be self-hosted.
LFM2.5-1.2B-Thinking is an open weights model that can be downloaded and self-hosted.