{"schema":"postcutoff/event@1","as_of":"2026-10-22T13:31:00+02:00","url":"https://postcutoff.com/e/2026-10-22-hugging-face-carbon-x-dna-model/","md":"https://postcutoff.com/e/2026-10-22-hugging-face-carbon-x-dna-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-22-hugging-face-carbon-x-dna-model","date":"2026-10-22","date_precision":"day","short_title":"Hugging Face releases Carbon-X, an open 14B model that lets users chat with DNA, close to GPT-6.1 Sol on DNA benchmarks at ~1/1,800 the cost","deck":null,"takeaway":"Hugging Face released Carbon-X, an Apache-2.0 14.8B model built on Qwen3-14B and trained on 300B tokens mixing DNA and English, so users can paste raw DNA into a chat and get explanations of variant effects, regulatory regions and organism groups.","category":"open-source","category_label":"Open source","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Hugging Face: Carbon-X model card","url":"https://huggingface.co/HuggingFaceBio/Carbon-X","type":"docs","group":"primary","domain":"huggingface.co"},{"n":2,"title":"WIRED: Hugging Face's new AI biology model lets you chat with DNA","url":"https://www.wired.com/story/hugging-face-new-ai-biology-model-chat-with-dna/","type":"press","group":"press","domain":"wired.com"}],"official":1,"filed":"2026-10-22","updated":"2026-10-22","orgs":["Hugging Face","Zhongguancun Academy","University of Naples Federico II"],"title":"Hugging Face releases Carbon-X, an open 14B model that lets users chat with DNA, close to GPT-6.1 Sol on DNA benchmarks at ~1/1,800 the cost","summary":"Hugging Face released Carbon-X, an Apache-2.0 14.8B model built on Qwen3-14B and trained on 300B tokens mixing DNA and English, so users can paste raw DNA into a chat and get explanations of variant effects, regulatory regions and organism groups. It averages 66.7% on five DNA benchmarks, 27 points above its base model and close to GPT-6.1 Sol (67.5%), and runs locally on a laptop.","key_facts":["Model card: 14.8B decoder-only, base Qwen/Qwen3-14B, Apache 2.0; one token stream for DNA and text; DNA tokenised as non-overlapping 6-mers","Benchmarks (Hugging Face): 66.7% average across five DNA benchmarks with thinking off, vs GPT-6.1 Sol 67.5%, at about 1/1,800 of the inference cost per problem; best of all tested models on coding-variant effects and next-base prediction","Training (WIRED): continued training on 300B tokens of DNA, English text and paired DNA–description examples from mammals, other vertebrates, invertebrates, plants, fungi and protozoa","Partners: Zhongguancun Academy (China) and University of Naples Federico II; Lewis Tunstall: 'We've unlocked a new capability in language models, which is fundamentally about being able to chat with DNA'","Weights: huggingface.co/HuggingFaceBio/Carbon-X (and GGUF)"],"key_numbers":[],"tags":["biology","genomics","dna","open-weights","hugging-face","variant-effect-prediction"],"science":null,"body_md":"## What happened\n\nHugging Face's biology team extended a general LLM's vocabulary with DNA 6-mers and kept training it on mixed genomic and text data,\nproducing a conversational DNA model small enough to run locally. WIRED notes Hugging Face agreed in September to be acquired by Nvidia.\n\n## Why it matters\n\nGenomic models like AlphaGenome and Evo 2 answer in numbers or sequences; Carbon-X answers in plain language, cheaply and openly,\nwhich widens access to variant interpretation (with the usual caveats for clinical use).","disputed":[],"related":[{"id":"2026-04-17-openai-gpt-rosalind","url":"https://postcutoff.com/e/2026-04-17-openai-gpt-rosalind/","date":"2026-04-17","date_precision":"day","short_title":"OpenAI launches GPT-Rosalind, a trusted-access reasoning model for life-sciences research","deck":null,"takeaway":"It is part of the 2026 race among frontier labs for AI-for-science products (Anthropic's Claude Science, Google's Gemini for Science).","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":10,"official":6,"filed":"2026-09-29","updated":"2026-10-13","orgs":["OpenAI"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-22","type":"filed","text":"Created (Techmeme)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-22","run":null,"sources_read":null,"updated":"2026-10-22","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":175,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":114,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":205,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":144,"in_training_data":false}],"short_url":null}