HF releases Carbon-X: 14B DNA-language model matches GPT-6.1 Sol at 1,000x lower cost
lvwerra · x · 2026-10-22
Hugging Face researchers released Carbon-X, a 14B hybrid DNA-and-natural-language model billed as the best open DNA model.
- Beats every open language model tested on DNA benchmarks and comes within a point of GPT-6.1 Sol at >1,000× lower inference cost
- Mid-trained on 300B tokens of interleaved DNA and text, then SFT (no distillation) and RL
- A new hybrid tokenizer encodes DNA with 3× fewer tokens than BPE
- Acts as a DNA specialist subagent: Kimi K3 gains 11.1 points when consulting Carbon-X
- Apache 2.0, runs locally on a laptop via llama.cpp, so DNA stays on your hardware
Related event: Hugging Face Open-Sources Carbon-X, a 14B DNA-Language Model(5 posts)→
More from Models
- Flint int4 hits 122.6 tok/s on Mac mini matching Qwen3.6-35B quality at 3.5x speed — _rockt · 2026-10-22
- Bayesian take: LLM benchmark noise means all models are probably tied — remilouf · 2026-10-22
- OpenAI's New Pricing Slammed for Zero Transparency as $500 Tier Reveals No Usage Numbers — Effective_Tap_9786 · 2026-10-22
- OpenAI's pricing pages never state actual usage limits, power users cry foul — Monstermage · 2026-10-22
- Nemotron 3.5 Super VL: NVFP4 on one Blackwell GPU beats BF16 on two, ~2.2x per-GPU throughput — TheZachMueller · 2026-10-22
- LFM2.5-24B-A2B Tested and Found Lacking: Looping Outputs, Broken Code, Full Configs Posted — tracagnotto · 2026-10-22