Hugging Face launches Carbon-X, a 14-billion-parameter DNA model built on Qwen3-14B
Hugging Face announced on Thursday the launch of Carbon-X, an open-source model with 14 billion parameters for DNA understanding and generation, obtained by training Qwen3-14B on genomic sequences and natural language. It integrates DNA sequences and natural language into a single model, allowing researchers to ask questions about specific DNA sequences, predict the effects of mutations, and generate new DNA sequences; it can also serve as a sub-agent to help other models interpret DNA sequences. Hugging Face says that on five DNA understanding and generation benchmarks, Carbon-X outperforms all other open-source models it evaluated, with an average score close to GPT-6.1 Sol, but at an inference cost per question of only 1/1800 of the latter, and 27 points higher than Qwen3-14B.
Why read this
AI score 71
The original text provides the model's parameter scale, training base, and benchmark comparisons, allowing readers to assess the viability of open-source specialized models in vertical scientific domains.
Topics
Body · AI translation
Hugging Face Launches New AI Model: Based on Qwen, It Lets Scientists "Chat with DNA"
Phoenix Tech Download the App for Exclusive Early Access October 23, 2026 07:56:24 From Beijing
Hugging Face
Phoenix Tech News, October 23 (Beijing Time) — According to Business Insider, AI company Hugging Face announced on Thursday the launch of a new AI model, Carbon-X, which is expected to help scientists more easily study DNA and develop new gene therapies.
Hugging Face said Carbon-X is an open model with 14 billion parameters for DNA understanding and generation. Carbon-X integrates DNA sequences and natural language into a single model: researchers can ask questions about specific DNA sequences, predict the effects of mutations, and generate new DNA sequences. It can also act as a specialized sub-agent, helping other models interpret DNA sequences that they themselves struggle to understand.
Built on the Qwen Large Model
Lewis Tunstall, a senior research scientist at Hugging Face, said Carbon-X is a first of its kind in combining DNA analysis and generation capabilities with natural language, enabling researchers to ask questions about DNA sequences and, in essence, "chat with DNA."
Hugging Face developed Carbon-X in collaboration with research laboratories in Italy and China; it is an open-source model. Hugging Face developed Carbon-X by training the existing language model Qwen3-14B using genomic sequences and natural language. The model was trained on DNA sequences from humans, other mammals, plants, and fungi.
Hugging Face said that on five DNA understanding and generation benchmarks, Carbon-X outperformed all other open-source models the company evaluated, with an average score close to GPT-6.1 Sol, but at only 1/1800 of the latter's inference cost per question. Compared with Qwen3-14B, Carbon-X's score improved by 27 points, indicating that by training directly on DNA data, the performance of open language models can be improved.
Carbon-X's benchmark score is close to GPT-6.1 Sol
Speaking about Carbon-X's application scenarios, Tunstall gave an example: researchers can provide the model with a DNA sequence and ask whether a particular mutation would increase a person's risk of disease. The model then gives a prediction and provides an explanation. It can also generate new DNA sequences, thereby helping researchers develop new gene therapies.
Preventing Over-Reliance on Big Companies
Tunstall said part of Hugging Face's motivation for developing Carbon-X is to prevent biology researchers from becoming dependent on large AI labs. He noted that AI has already had a disruptive impact on the field of mathematics.
"If you want to truly push the frontier of mathematical research, you probably have to work at an AI lab like OpenAI or Anthropic, because they have the best math models," Tunstall said. He believes similar situations could arise in other scientific fields.
He added: "We want to provide tools to the open research community so they don't have to rely entirely on a single external vendor."
Researchers can run Carbon-X on their own computers without sharing sensitive patient data with external AI companies. Tunstall also said that some of the misaligned behaviors observed in large models have not yet appeared in smaller, more specialized models, such as the problems exposed by the well-known incident in July this year when an OpenAI agent breached Hugging Face.
Tunstall said general-purpose chatbots sometimes also refuse to answer legitimate biology questions posed by researchers because they mistakenly believe the questions are attempts to "design biological weapons." He said that to prevent model misuse, Carbon-X's training data explicitly excludes virus-related data.
Although Carbon-X is likely to be used mainly by researchers, Tunstall said the model is a small step toward the future, when AI is expected to help provide more personalized medical services.
"I think the ultimate goal is to achieve personalized medicine, where each of us can use our own medical records and genomic data to ultimately find and perhaps even design treatment plans that suit us," he said. (Author/Xiaoyu)
For more first-hand news, please download the Phoenix News app and subscribe to Phoenix Tech. For in-depth reporting, search "Phoenix Tech" on WeChat.