Skip to main content
LFM2.5
Compact tier
Tool calling

LFM2.5 350M

Compact on-device instruct — teacher for the 230M distill.

by Liquid AI

LFM2.5 group

Overview

LFM2.5-350M is the compact instruct hybrid used as the distillation teacher for 230M. Same edge-first architecture with stronger out-of-the-box tool use and multilingual coverage.

LFM2.5 350M 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

  • Edge agent prototypes with a bit more headroom than 230M
  • Multilingual tool-calling at sub-1B cost
  • Domain LoRA when 230M underfits

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
Parameters350M
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.