LiquidAI: LFM2-2.6B
Analysis Summary
LFM2-2.6B is LiquidAI's smallest publicly available model, a 2.6B parameter text-only system with no vision, tool use, or function calling. Its benchmark scores are among the lowest in the current field: intelligence index 2.7, coding index 1.4, and an MMLU Pro of 0.298 that is below random chance on many tasks.
For businesses, the use case is narrow. It could serve as a fast, cheap classifier or keyword extractor in a pipeline where a larger model handles anything requiring actual reasoning. The 32K context window is limiting, and there is no multimodal or agentic capability to speak of.
At $0.01 input and $0.02 output per million tokens, it is one of the cheapest models available. Its value is purely in cost-per-token for trivial tasks; any workflow requiring reliable language understanding should use a more capable model.
Assessed June 17, 2026
Editorial notes
LiquidAI LFM2-2.6B is a very small text-only model with near-minimal benchmark scores, useful only as an ultra-cheap component in high-volume, low-complexity pipelines.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How LiquidAI: LFM2-2.6B compares
LiquidAI: LFM2-2.6B ranks #352 of 380 AI models we track for overall intelligence, #302 of 317 for coding, #278 of 292 for agentic tasks. Its 33K-token context window is larger than 32% of the models we list. At $0.01 per million input tokens it is cheaper than 78% of comparable models.
About LiquidAI: LFM2-2.6B
LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does LiquidAI: LFM2-2.6B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
liquid/lfm-2.2-6b
|
| Provider | liquid |
| Release Date | October 20, 2025 |
| Context Length | 32,768 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.01 | $0.000010 |
| Output | $0.02 | $0.000020 |
External Resources
Frequently asked questions about LiquidAI: LFM2-2.6B
How much does LiquidAI: LFM2-2.6B cost?
LiquidAI: LFM2-2.6B costs $0.01 per million input tokens and $0.02 per million output tokens.
What is the context window of LiquidAI: LFM2-2.6B?
LiquidAI: LFM2-2.6B has a context window of 32,768 tokens (33K).
Is LiquidAI: LFM2-2.6B good for coding?
On our coding benchmark index, LiquidAI: LFM2-2.6B ranks #302 of 317 models, placing it in the broader range of the field for code generation and debugging.
Who created LiquidAI: LFM2-2.6B?
LiquidAI: LFM2-2.6B is developed by LiquidAI and was released on October 20, 2025.
