---
id: "2026-10-22-hugging-face-carbon-x-dna-model"
url: "https://postcutoff.com/e/2026-10-22-hugging-face-carbon-x-dna-model/"
as_of: "2026-10-22T13:31:00+02:00"
date: "2026-10-22"
date_precision: day
category: open-source
importance: 3
confidence: high
status: [Confirmed]
sources: 2
editor: human editor
human_review: null
version: null
---

As of: 2026-10-22 13:31 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-10-22-hugging-face-carbon-x-dna-model/

# 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

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)

## What happened

Hugging Face's biology team extended a general LLM's vocabulary with DNA 6-mers and kept training it on mixed genomic and text data,
producing a conversational DNA model small enough to run locally. WIRED notes Hugging Face agreed in September to be acquired by Nvidia.

## Why it matters

Genomic models like AlphaGenome and Evo 2 answer in numbers or sequences; Carbon-X answers in plain language, cheaply and openly,
which widens access to variant interpretation (with the usual caveats for clinical use).

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 175 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 114 days after its cutoff
- Gemini 4 Argon (training cutoff March 2026): 205 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 144 days after its cutoff

## Sources

1. [Hugging Face: Carbon-X model card](https://huggingface.co/HuggingFaceBio/Carbon-X) (huggingface.co, docs)
2. [WIRED: Hugging Face's new AI biology model lets you chat with DNA](https://www.wired.com/story/hugging-face-new-ai-biology-model-chat-with-dna/) (wired.com, press)

## Changes

- 2026-10-22 (filed): Created (Techmeme)

## Related

- 2026-04-17: [OpenAI launches GPT-Rosalind, a trusted-access reasoning model for life-sciences research](https://postcutoff.com/e/2026-04-17-openai-gpt-rosalind/index.md)