Skip to main content
LFM2.5
Compact tier
Tool calling

LFM2.5 1.2B Instruct

Sub-2B that rivals larger models for agents, extraction, and RAG.

by Liquid AI

LFM2.5 group

Overview

LFM2.5-1.2B-Instruct is Liquid's flagship small instruct model — 28T-token pretrain plus multi-stage RL, ChatML tool calling, and day-one support for Transformers, vLLM, and llama.cpp. Strong on agentic tasks and RAG; not aimed at heavy coding or knowledge-intensive work.

LFM2.5 1.2B Instruct trains on your agent's own traces with LoRA adapters or full finetuning, is benchmarked against your production model before any traffic moves, and serves through the same OpenAI-compatible API as every Overmind model. The final weights are yours to download and run anywhere.

Good for

  • Agentic tool-calling and data extraction
  • RAG on edge or cost-sensitive cloud
  • Fast LoRA specialization under 1GB-class footprints

More in LFM2.5

← Back to all models
Train now

Specs & cost

Cost to trainfrom $0.50
Cost to run (1M tok)from $2.50
GroupLFM2.5
FamilyLiquid AI
Parameters1.2B
TierCompact
Context window32K
Max training context32K
Tool callingYes
Methods—
Train now
Training docs

On Overmind

  1. 01 Train on your data

    LoRA or full finetuning on a training-intent dataset from your agent's traces. Overmind recommends tiers from your data stats; you can edit every setting.

  2. 02 Benchmark vs production

    Each finished model is scored on your eval set with your rubric against the model your agent runs today. The headline is the baseline delta per metric.

  3. 03 Serve and own the weights

    Succeeded runs deploy automatically to Inference through the same OpenAI-compatible API. The final weights are yours to download and run anywhere.