Model Releases
▲ Hugging Face just released Carbon-X, an open 14.8B model that reads raw DNA inside a chat and answers in English. The key idea is 1 decode…
▲ Hugging Face just released Carbon-X, an open 14.8B model that reads raw DNA inside a chat and answers in English. The key idea is 1 decoder for both DNA and text. A hybrid tokenizer keeps Qwen3's te
▲ Hugging Face just released Carbon-X, an open 14.8B model that reads raw DNA inside a chat and answers in English. The key idea is 1 decoder for both DNA and text. A hybrid tokenizer keeps Qwen3's text vocabulary and turns DNA into 6-base tokens. There is no separate DNA encoder: it starts from Qwen3-14B, then gets 302B tokens of DNA + text mid-training, SFT and RL. Across 5 DNA benchmarks it averages 66.7% with thinking off, vs 67.5% for GPT-6.1 Sol at max effort. It leads every model tested on BioReason Coding (74.9%) and NextBase (39.4%). It is a trade-off though: splice-site questions score only 29.8%, and it is not clinically validated. Weights are Apache 2.0 and fit on 1 x 80 GB GPU. Hugging Face estimates about 300 to score 2.4M ClinVar variants, vs 32K to $4M on frontier models...... Full analysis: https://www.marktechpost.com/2026/10/25/hugging-face-carbon-x-14b-dna-language-model/ Model: http://huggingface.co/HuggingFaceBio/Carbon-X Blog: http://huggingface.co/spaces/HuggingFaceBio/Carbon-X-Release Repo: http://github.com/huggingface/carbon GGUF: http://huggingface.co/HuggingFaceBio/Carbon-X-GGUF @huggingface @_lewtun @LoubnaBenAllal1 @ClementDelangue
Related
Source: Clem Delangue (X) | 2026-10-25