Model Library
Liquid AIReleased January 5, 2026LFM2.5-VL-1.6B
Liquid AI · Released January 5, 2026
Intelligence score
1
At a glance
- Intelligence
- 1
- Speed
- 421.4tokens/sec
- Latency
- 4.36stime to first token
- Input price
- Not published
- Output price
- Not published
- Context window
- 32Ktokens
- Parameters
- 1.6billions
Summary
Comparison summary
LFM2.5-VL-1.6B scores 1 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 3). LFM2.5-VL-1.6B generates output at 421.4 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 85.1 t/s).
Specifications
Technical specifications
| Model name | LFM2.5-VL-1.6B |
|---|---|
| Provider | Liquid AI |
| Release date | January 5, 2026 |
| Intelligence score | 1 |
| Speed | 421.4 tokens/sec |
| Latency (TTFT) | 4.36s |
| Input price | Not published |
| Output price | Not published |
| Context window | 32,000 tokens |
| Parameters | 1.6B |
| Reasoning | No |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | lfm 1 |
| API availability | — |
| Source | Model Intelligence legacy profile: lfm2-5-vl-1-6b |
FAQ · 17
Frequently asked questions
LFM2.5-VL-1.6B was released on January 5, 2026.
LFM2.5-VL-1.6B was created by Liquid AI.
LFM2.5-VL-1.6B scores 1 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 3).
LFM2.5-VL-1.6B generates output at 421.4 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 85.1 t/s).
LFM2.5-VL-1.6B has a time to first token (TTFT) of 4.36s (based on the median across providers serving the model), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 0.84s).
No, LFM2.5-VL-1.6B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
LFM2.5-VL-1.6B supports text and image input.
LFM2.5-VL-1.6B supports text output.
Yes, LFM2.5-VL-1.6B supports image input and can analyze, describe, and answer questions about images.
Yes, LFM2.5-VL-1.6B is multimodal. It can process text and image input and generate text output.
LFM2.5-VL-1.6B 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-VL-1.6B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
LFM2.5-VL-1.6B has 1.6 billion parameters.
LFM2.5-VL-1.6B is released under the lfm 1.0 license. This license allows commercial use.
LFM2.5-VL-1.6B achieves a score of 1 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, LFM2.5-VL-1.6B is available via API through 1 provider.
LFM2.5-VL-1.6B is available through 1 API provider.