Skip to main content
Gemma 4
Small tier
Tool calling

Gemma 4 E2B

Edge multimodal Gemma 4 — text, image, and audio at phone/laptop scale.

by Google

Gemma 4 group

Overview

Gemma 4 E2B is the smallest instruct multimodal (text/image/audio) with 128K context and built-in thinking control. Tuned for phones, ASR-adjacent jobs, and cheap LoRA on a single GPU.

Gemma 4 E2B 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 multimodal assistants
  • Cheap LoRA on coding/tool tasks
  • Thinking-mode experiments at small size

More in Gemma 4

← Back to all models
Train now

Specs & cost

Cost to trainfrom $0.55
Cost to run (1M tok)from $4.00
GroupGemma 4
FamilyGoogle
ParametersE2B (~5.1B)
TierSmall
Context window128K
Max training context128K
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.