Skip to main content
Gemma 4
Large tier
Tool calling

Gemma 4 31B

Strongest dense Gemma 4 — max quality at 256K.

by Google

Gemma 4 group

Overview

Gemma 4 31B is the flagship dense instruct model. Pick it when quality beats MoE speed and you can afford H100-class train/serve (QLoRA recommended).

Gemma 4 31B 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

  • Maximum-quality coding and reasoning LoRA
  • Long-context multimodal document work
  • Evals where 26B-A4B leaves quality on the table

More in Gemma 4

← Back to all models
Train now

Specs & cost

Cost to trainfrom $2.50
Cost to run (1M tok)from $10.00
GroupGemma 4
FamilyGoogle
Parameters31B
TierLarge
Context window256K
Max training context256K
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.