hydrogen-1.0
hydrogen-1.0 is Text Generation model with 753B parameters. Download, explore files and run it on Hugging Face.. It is ranked #223 on the AI Radar, in Frontier models, first seen 3 days ago and shared in 3 posts (10.7k views).
deep-principle/Hydrogen-1.0 · Hugging Face Hugging Face Log In Sign Up ","pad_token":"<|endoftext|>"},"chat_template_jinja":"[gMASK]<sop>\n{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}\n{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}\n{%- set clear_thinking = clear_thinking if clear_thinking is defined else false -%}\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n…
What people said about hydrogen-1.0 on X
Hydrogen 1.0 🔬 Impressive open model built for scientific discovery - Based on GLM 5.3 - 1M context window - MIT license + with BF16, NVFP4,MXFP4 variants https://huggingface.co/deep-principle/Hydrogen-1.0
— @AdinaYakup, 1 days ago · 65 likes · see the post
😎太牛了吧！基于GLM-5.3后训练的Hydrogen-1.0，在前沿科研基准上反超GPT-6-Astra！ Deep Principle发布首个开源科学发现模型Hydrogen-1.0，用实验室完整记录+发现轨迹（含失败实验）对GLM-5.3做后训练。 核心亮点： 1️⃣基座实力兑现：FrontierScience-Research 38.3% > GPT-6-Astra的33.3%；GPQA-Diamonds 93%。 2️⃣专营模型实际用处： 🔹一句话意图直接生成实验方案与协议 🔹自动写代码、跑分子动力学（GROMACS）、修拓扑错误并分析结果 🔹探索反应网络、解读NMR谱图…
— @NFT_Chen, 3 days ago · 58 likes · see the post
An open model just beat GPT 6 Astra on science research. At least on its makers own evals. @DeepPrinciple released Hydrogen 1.0. It's GLM 5.3 post-trained for science. And it's available with 4bit versions for NVIDIA and AMD. https://huggingface.co/deep-principle/Hydrogen-1.0
— @plotarmordev, 3 days ago · 20 likes · see the post
Alternatives to hydrogen-1.0
- Thinking Machines Lab — Mantic have been using Tinker since it launched. This guest post is a technical deep dive on what they have built so…
- openai.com —
- Tencent Hy — Tencent Hy
- clocktowerbench.com — You can see the full benchmark at the website, and I’ve also made it so that you and your friends can play again the AIs
- Claude — Basecamp for Claude is live!
- Mercor — Evaluate frontier AI models with Mercor's APEX AI Benchmarks & Leaderboards. Measure AI productivity across software…
hydrogen-1.0 in numbers
- Rank on the AI Radar: #223 of 10389
- Shared in 3 posts by 3 accounts: @AdinaYakup, @NFT_Chen, @plotarmordev
- 10.7k views on those posts
- First seen 3 days ago, last shared 1 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Frontier models
FAQ
What is hydrogen-1.0?
Text Generation model with 753B parameters. Download, explore files and run it on Hugging Face. It was first shared on X 3 days ago and is ranked #223 on the AI Radar.
Is hydrogen-1.0 free?
It is open source.
Who shared hydrogen-1.0?
3 accounts on X, including @AdinaYakup, @NFT_Chen, @plotarmordev, in 3 posts totalling 10.7k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.7k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 13:30 UTC. Full method.