L
LFM3-1.7B
liquid-ai · Released Oct 2026
Conditional
LFM3-1.7B is a small open-weight text model from Liquid AI that we would pick for on-device agents that call tools and return structured outputs, or as a base for domain fine-tuning. The deciding caveat: Liquid's own model card says it is not recommended for agentic coding or complex multi-step reasoning. It suits developers shipping edge agents; we have not tested it.
Is it right for you?
Good for
- Local agents, tool calling and structured outputs. Liquid's model card lists these as the intended uses.
- Domain-specific fine-tuning of a small model. The model card lists it as an intended use.
- Memory-constrained devices. Liquid says the text model fits in about 1 GB at 4-bit precision.
Not good for
- Agentic coding or complex multi-step reasoning. The model card says it is not recommended for either "due to its small size".
How it performs by task
Agentic coding
Poor
The model card says it is not recommended for agentic coding.
Complex multi-step reasoning
Poor
The model card says it is not recommended for complex multi-step reasoning.
Pricing
Input
$0.08 / 1M tokens
Output
$0.20 / 1M tokens
Context
256K ctx; cached input $0.02
No verdict changes yet
The clock starts day one. Changes land here as our verdict evolves.
Sources
- Liquid AI LFM3 launch postNov 2026
- LFM3-1.7B model card (Hugging Face)Nov 2026
- Liquid AI pricingNov 2026
Verification log
- Pricing· No changes
Automated agent