Gemini 4 Hydrogen Is Cloud Only: No Weights, No Local Run

Google DeepMind introduced Gemini 4 Hydrogen on 12 November 2026 (Google DeepMind, 2026). It is the fast member of the Gemini 4 family, built for everyday coding and agentic workflows, next to the frontier models Gemini 4 Carbon and Gemini 4 Argon. Short answer for local users: you cannot run it. Gemini 4 Hydrogen is a cloud-only model, with no published weights and no published parameter count, so it cannot run on any Mac, including a 512GB Mac Studio.

TL;DR: Gemini 4 Hydrogen costs $1.50 per million input tokens and $7.50 per million output tokens, flat across its 1 million-token context window. Google says it scores 51 on the Artificial Analysis Intelligence Index at its default high thinking level and 54 at xhigh, ahead of Argon's 50. It runs only on Google's servers. If you want a Google model on your own machine, the answer is Gemma 4.

What did Google announce?

The announcement by Koray Kavukcuoglu, SVP of Google DeepMind, positions Hydrogen as the execution model: Carbon and Argon handle deep, long-horizon reasoning, and Hydrogen writes code, runs tests and verifies changes. The benchmark table on Google's Gemini models page and the evaluation methodology give the scores below.

The Intelligence Index figures are Google's own reporting ("51 vs. 50, and reaching 54 at its highest xhigh thinking setting"). Google's methodology notes that the Terminal-Bench 4.1 and Agents' Last Exam v1.1 results for Hydrogen are self-computed. Against Gemini 3.8 Flash, Google says Hydrogen finishes tasks 2.5 times faster at its high default setting and more than triples its Terminal-Bench 4.1 score (57% vs. 18.2%).

Access, per the announcement:

• Developers: all tiers of Google AI Studio and the Gemini API.
• Enterprises: Gemini for business.
• Consumers: the Gemini app and Google Search, plus paid Google AI Pro and Ultra subscribers in Google Antigravity.

TestingCatalog covered the rollout the same day.

How does Hydrogen fit with Carbon and Argon?

Google describes Hydrogen as a model that can stand on its own or pair with Gemini 4 Carbon and Gemini 4 Argon. In Antigravity, a new Orchestrator switches between Carbon and Hydrogen within one session: Carbon plans and coordinates, Hydrogen powers the worker and verifier agents. It is also cheaper per token than Carbon, which launched at $2 per million input tokens and $10 per million output tokens.

All three Gemini 4 models are cloud only. None of Google's posts mentions weights for any of them.

Can a 512GB Mac Studio run Gemini 4 Hydrogen?

No. There is nothing to download: Google has published no weights for Hydrogen, and the Hugging Face API lists no Hydrogen repository under Google's account as of 13 November 2026. Google has not given a parameter count either, so the model cannot be sized against any machine, and we will not guess one. A Mac Studio with 512GB is the largest single computer we track, and it still cannot run a model whose weights are not public. Hydrogen runs only on Google's servers.

ModelFit does not add a model page or a dataset entry for cloud-only models. That will only change if Google publishes weights that llama.cpp or mlx-lm can load.

What can a Mac run locally instead?

Google's open-weight family is Gemma. Gemma 4 is far smaller than any Gemini model, but it runs on ordinary hardware:

• Gemma 4 31B, the dense flagship, loads in about 20 GB at Q4, so a 32GB Mac runs it.
• Gemma 4 26B-A4B, the mixture-of-experts version, loads in about 16 GB at Q4 and is the faster of the two, which makes it the closest local match to Hydrogen's role as a quick everyday model.

Our Gemma 4 GPU requirements guide lists every size in GB. If you own a 512GB Mac Studio and want the biggest model it can hold, our best LLMs for the M5 Ultra 512GB ranks the open-weight models that fit. None of them is a drop-in copy of Hydrogen, but they run offline, privately, and without a per-token bill. For a pick matched to your own machine, use the ModelFit wizard or npx @modelfit/cli@latest.

FAQ

Can you run Gemini 4 Hydrogen locally?

No. Gemini 4 Hydrogen is cloud only. Google has published no weights and no parameter count, so it cannot run on a Mac or a PC, whatever the memory.

How much does Gemini 4 Hydrogen cost?

$1.50 per million input tokens and $7.50 per million output tokens, flat across the whole 1 million-token context window.

Where can I use Gemini 4 Hydrogen?

In Google AI Studio and the Gemini API (all tiers), Gemini for business, the Gemini app, Google Search, and Google Antigravity for paid Google AI Pro and Ultra subscribers.

What is the difference between Hydrogen, Carbon and Argon?

Carbon and Argon are Google's frontier models for deep, long-horizon reasoning. Hydrogen is the fast execution model for everyday coding and agents, and it costs less per token. Google says Hydrogen scores 51 on the Artificial Analysis Intelligence Index at high, against 50 for Argon.

What is the best Google model I can run locally?

Gemma 4. The 31B dense model loads in about 20 GB at Q4 and the 26B-A4B mixture-of-experts model in about 16 GB.

Sources

• Google DeepMind, Introducing Gemini 4 Hydrogen, 12 November 2026: https://deepmind.google/blog/introducing-gemini-4-hydrogen/
• Google DeepMind, Gemini models (benchmark table): https://deepmind.google/models/gemini/
• Google DeepMind, Gemini 4 Hydrogen model evaluation methodology: https://storage.googleapis.com/deepmind-media/gemini/gemini_4_hydrogen_model_evaluation.pdf
• TestingCatalog, Google launches Gemini 4 Hydrogen for Pro and Ultra users, 12 November 2026: https://www.testingcatalog.com/google-launches-gemini-4-hydrogen-for-pro-and-ultra-users/
• Google DeepMind, Gemini 4 Carbon is now available, 10 November 2026: https://deepmind.google/blog/gemini-4-carbon-is-now-available/
• Google, Introducing Gemini 4 Argon, 13 October 2026: https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-argon/
• Hugging Face API, Google models matching "hydrogen", read 13 November 2026: https://huggingface.co/api/models?author=google&search=hydrogen