Gemma 4 (31B dense + 26B A4B MoE)

Google's April 2026 refresh — Arena top 5 in its first week, 256K context native, vision + audio multimodal. Big news: Gemma 4 moved to Apache 2.0 from the custom Gemma Terms. The current Apache-2.0 "best dense under 70B" pick.

License: Apache 2.0 (moved off Gemma Terms) · Context: 256K · Released: April 2, 2026

The decision in five lines

The call: Buy — for chat
Best for: chat · docs
Runs on: 16 hardware picks fit (cheapest: Minisforum UM890 Pro · $463)
Watch out: Tight VRAM budgets under 16 GB — even Gemma 4 26B MoE wants 15 GB at Q4.
Evidence: Estimated · last verified April 2026

31B dense: PARAMETERS
DENSE + MOE: TYPE
256K: CONTEXT
~18 GB (31B dense) / ~15 GB (26B MoE): VRAM AT Q4

Where we recommend this

Every tier slot in the planner where this model is a top or alternate pick. Pulled live from planner.js — when the planner refreshes, this table stays current.

CHAT · TOP

Gemma 4 31B DenseGoogle April 2 2026 release; Arena top 5, 256K context, vision+audio native; Apache 2.0.

CHAT · HIGH

Gemma 4 26B MoE (3.8B active)Open Arena top 10 at 3.8B active compute; calm and fast.

DOCS · TOP

Gemma 4 31B (256K context)256K context with vision+audio; calmer long-context behaviour than the 35B-A3B MoE on dense retrieval prompts.

DOCS · HIGH

Gemma 4 31B (256K context)31B dense with 256K context; Gemma commercial-permissive terms; Arena top 5.

The call

Google's April 2026 refresh — Arena top 5 in its first week, 256K context native, vision + audio multimodal. Big news: Gemma 4 moved to Apache 2.0 from the custom Gemma Terms. The current Apache-2.0 "best dense under 70B" pick.
When not to use: Tight VRAM budgets under 16 GB — even Gemma 4 26B MoE wants 15 GB at Q4. For those budgets, Qwen 3.5 9B fits better.

Runner notes

Ollama tags `gemma4:31b` and `gemma4:26b`. Ollama may lag on the audio modality path — use llama.cpp head for full multimodal. MoE routing overhead can hurt vLLM concurrency vs dense equivalents under heavy batching.

License: Apache 2.0 (moved off Gemma Terms)
Released: April 2, 2026
Maker: Google
Model card: huggingface.co/google/gemma-4-31B-it →

Hardware that fits

Every hardware pick whose memory fits this model at the quant we recommend. Sorted cheapest-first — the top row is your best-value fit. Click through for the full buyer’s guide.

Next step

Find-by-model — see what hardware runs this→