Context
128K tokens (~64 books)
Input $/1M
n/a
Output $/1M
n/a
Type
multimodal
License
Proprietary
Benchmarks
0 tested
Data as of
About
LFM3-Omni-2B is Liquid AI's omni model in the LFM3 family · about 2.2B parameters · vision and audio input · 128,000 token context · open weights under the LFM 1.0 license on Hugging Face as LiquidAI/LFM3-Omni-2B.
No benchmark data available yet.
Links
Research
Documentation
Community
BenchGecko API
lfm-3-omni-2b
Specifications
- Typemultimodal
- Context128K tokens (~64 books)
- ReleasedOct 2026
- LicenseProprietary
- StatusActive
Available On
Learn More
Share & Export
Frequently Asked Questions
LFM3-Omni-2B is a proprietary multimodal AI model by liquid, released in October 2026. Context window: 128K tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteJais 3 0.9B · MBZUAIGemma 3 12B (free) · Google DeepMindBenchmarks
Key facts · as of 2026-10-29
- LFM3-Omni-2B by liquid. Not enough public benchmark scores to rank yet.
- List price n/a input · n/a output per 1M tokens (as of 2026-10-29).
How to cite · data as of 2026-10-29
LFM3-Omni-2B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-29. https://benchgecko.ai/model/lfm-3-omni-2b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP