Skip to main content
Gemma 4
Small tier
Tool calling

Gemma 4 E4B

Default small Gemma 4 — stronger than E2B for laptop multimodal use.

by Google

Gemma 4 group

Overview

Gemma 4 E4B is the recommended small instruct tier for local multimodal work. Same 128K context and thinking controls as E2B with more capacity for coding and tool use.

Gemma 4 E4B 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

  • Laptop multimodal + tool agents
  • Coding LoRA when E2B underfits
  • Speech/text fine-tunes on a single GPU

More in Gemma 4

← Back to all models
Train now

Specs & cost

Cost to trainfrom $0.75
Cost to run (1M tok)from $4.00
GroupGemma 4
FamilyGoogle
ParametersE4B (~8B)
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.