Google · Open Weights · Apache 2.0
Gemma 4: Every Model, and What Hardware Actually Runs It
Gemma 4 (launched March 31 / April 2, 2026, Apache 2.0) is the most consumer-runnable open model family of the summer 2026 releases. Five members, five hardware tiers: E2B and E4B run fully offline on phones and Raspberry Pi (Google's claim); the 12B "Unified" — added June 3 — takes text, audio, and image in one model with 256K context and fits a 12GB card at Q4 (~7-8 GB, our estimate); the 26B-A4B MoE and 31B dense fit a single 24GB card quantized (our estimate), and Google says both fit a single 80GB H100. Below: every family member mapped to real hardware, with every estimate labeled as one.
Key takeaways
- →Five models, phone to H100 — E2B (~2.3B effective), E4B (~4.5B effective), 12B Unified, 26B-A4B MoE, 31B dense.
- →Apache 2.0, open weights — no custom license restrictions.
- →12B Unified is the headline — text + audio + image input in one model, up to 256K context. Added June 3, 2026.
- →Phone and Pi are official targets — Google claims E2B/E4B run fully offline on phones, Raspberry Pi, and Jetson Orin Nano.
- →24GB VRAM unlocks the whole family — 26B-A4B at Q4 ≈ ~15-16 GB, 31B at Q4 ≈ ~18-19 GB (our estimates).
Quick verdict
If you run models locally, Gemma 4 is the family to know in 2026. Many 2026 open releases target datacenter hardware; Gemma 4 goes the other way: every member of the family targets hardware people actually own, from phones up to a single prosumer GPU.
The short version: own a 12GB card, run the 12B Unified. Own a 24GB card, run 26B-A4B (faster) or 31B (denser). Own a Raspberry Pi or want offline-on-phone, E2B/E4B are Google's explicit targets. For install steps, our Gemma local setup guide covers the tooling.
The family at a glance
The core family launched March 31 / April 2, 2026 (Google's announcement). The 12B Unified joined on June 3, 2026, confirmed on Google's official Gemma releases page. All under Apache 2.0. Google's release notes document input modalities only for the 12B Unified (text + audio + image), so that's the only member where we list them.
| Model | Parameters | Notable |
|---|---|---|
| E2B | ~2.3B effective | Phones, Raspberry Pi, Jetson Orin Nano — fully offline (Google's claim) |
| E4B | ~4.5B effective | Same targets as E2B, more capable |
| 12B Unified | 12B | Text + audio + image input in one unified model, up to 256K context. Added June 3, 2026 |
| 26B-A4B | 26B total / ~4B active (MoE) | MoE speed: quality of its size class, compute of a ~4B |
| 31B | 31B dense | The full-strength dense flagship; fits a single 80GB H100 (Google's claim) |
Hardware tiers: what runs where
Quantized sizes below are our estimates from standard Q4 arithmetic — Google publishes hardware targets, not GGUF file sizes. Treat them as planning numbers, and leave headroom for context.
| Your hardware | Best Gemma 4 fit | Notes |
|---|---|---|
| Phone / Raspberry Pi / Jetson Orin Nano | E2B, E4B | Google's stated targets — fully offline |
| 8GB VRAM | E4B comfortably; 12B Unified at Q4 is tight | 12B Q4 ≈ ~7-8 GB (estimate) — short context only on 8GB |
| 12GB VRAM | 12B Unified at Q4 | Comfortable fit with context headroom (estimate) |
| 16GB VRAM | 12B Unified with long-context headroom | 26B-A4B Q4 ≈ ~15-16 GB (estimate) — too tight once context is loaded |
| 24GB VRAM | 26B-A4B or 31B at Q4 | 26B-A4B ≈ ~15-16 GB, 31B ≈ ~18-19 GB (estimates) |
| Apple Silicon, 32GB+ unified memory | 26B-A4B or 31B at Q4 | Unified memory covers the same estimates as a 24GB card |
| 80GB H100 | 26B-A4B or 31B | Single-GPU fit is Google's claim |
On an 8GB card, E4B is the honest recommendation — the 12B squeeze works but leaves you no context room. More 8GB options in best local AI models for 8GB RAM. Sitting at 16GB and weighing alternatives? See the best LLMs for 16GB VRAM.
12B Unified: text, audio, image — one model
The June 3 addition is the most interesting member of the family. Gemma 4 12B "Unified" is a single unified multimodal architecture: it takes text, audio, and image input in one model, with up to 256K context. One model, one download — no separate vision or audio models to juggle.
For local use, that simplicity matters more than it sounds. Multimodal-local setups have historically meant juggling two or three models and hoping the glue code holds. A 12B that does all three inputs and fits a 12GB card at Q4 (~7-8 GB, our estimate) collapses that stack into one download. The 256K window is the other half of the story — enough for entire codebases or long transcripts, if your VRAM leaves room for it.
What defines the Gemma 4 lineup
Three structural choices define the Gemma 4 lineup. First, MoE: 26B-A4B carries 26B total parameters but activates only ~4B per token — its compute cost per token is closer to a small model's. Second, the E2B/E4B "effective parameter" models, built for phones and single-board computers as first-class targets rather than afterthoughts. Third, the unified multimodal 12B described above.
If you're currently running Gemma 2 9B, the 12B Unified is the natural upgrade path — similar hardware tier, plus audio and image input. If you're on Gemma 2 27B, the 26B-A4B gives you the same size class with MoE speed, and the 31B is the straight dense successor.
Ecosystem proof: local speech-to-speech in production
A fair question about any new family: is anyone actually building on it? For Gemma 4, yes — and the example is concrete. On July 1, 2026, Hugging Face and Cerebras open-sourced a complete local speech-to-speech pipeline: Nvidia Parakeet handles speech recognition, Gemma 4 31B is the language model in the middle, and Qwen3-TTS produces the spoken reply.
That pipeline isn't a demo repo — it already powers 9,000+ Reachy Mini robots. A fully local, open-weight voice assistant stack with Gemma 4 at its core, shipping in physical products three months after the family launched. That's the kind of ecosystem signal that usually takes a year.
FAQ
What is Gemma 4?
Can Gemma 4 run on a Raspberry Pi?
How much VRAM does Gemma 4 12B need?
Should I upgrade from Gemma 2 to Gemma 4?
Is Gemma 4 open source? What license does it use?
Can Gemma 4 do speech / audio locally?
Related models
- → Gemma 2 9B — the previous mid-size Gemma; 12B Unified is its successor tier
- → Gemma 2 27B — previous large Gemma; compare with 26B-A4B and 31B
- → Gemma 3 270M — the tiniest Gemma, for microcontroller-class tasks
- → GPT-OSS — OpenAI's open-weight alternative in the prosumer tier
- → Best Ollama models — where the Gemma family sits in the wider local lineup
Go from reading about AI to building with AI
20 structured courses. Hands-on projects. Runs on your machine. Start free.
Written by the Local AI Master Team
The team behind Local AI Master
We build Local AI Master around practical, testable local AI workflows: model selection, hardware planning, RAG systems, agents, and MLOps. The goal is to turn scattered tutorials into a structured learning path you can follow on your own hardware.