Skip to main content
LFM3
Compact tier
Tool calling

LFM3 1.7B

1.7B agent model with a 256K window and tool calling.

by Liquid AI

LFM3 group

Overview

LFM3-1.7B is Liquid's text instruct checkpoint: 24 tri-hybrid layers, tool calling, and a 256K window. Thinking is off when enable_thinking is false.

LFM3 1.7B trains on your agent's own traces, can be 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

  • Tool-calling and agent loops at compact size
  • Instruction following on a 256K window
  • Domain LoRA on a single GPU
← Back to all models
Train now

Specs & cost

Cost to trainfrom $0.55
Cost to run (1M tok)from $2.50
GroupLFM3
FamilyLiquid AI
Parameters1.7B
TierCompact
Context window256K
Max training context128K
Tool callingYes
MethodsLoRA · Full
Train now
Training docs

On Overmind

  1. 01 Train on your data

    Fine-tune on a training 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.