ESM C, setting a new state of the art for protein language models
Hey HN! We're releasing ESM C, a series of protein language models that set a new state of the art. By training on metagenomics and fine-tuning on UniRef, we're able to match ESM2 650M with ESM C 300M, and ESM C 6B has incredible unsupervised contact precision performance. These models are meant to be used as base models and representation learning models for protein sequences, and we'll release a preprint describing exact details soon.
ESM C, setting a new state of the art for protein language models launched on December 4, 2024 with 11 votes, #1,640 of 5,365 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
ESM C is a series of protein language models trained on metagenomics data and fine-tuned on UniRef sequences. Designed for researchers working with protein sequences, these models serve as base models for representation learning tasks. The series achieves notable efficiency, with the 300M parameter version matching the performance of a larger competitor model, while the 6B version demonstrates strong unsupervised contact prediction capabilities.
written from the facts on this page · September 2026
From the sources
Today we’re introducing ESM Cambrian, a next generation language model trained on protein sequences at the scale of life on Earth. ESM C models define a new state of the art for protein representation learning. AI is beginning to unlock an era of digital biology where we can use computation to go beyond the limits of experiments in the physical world. The universe of protein function is so vast and complex that we lack the ability to fully characterize it experimentally, and for many applications, we need to engineer functions that go beyond those in nature. The physical limitations of performing experiments in the real world mean that unsupervised learning—algorithms that can learn from…from evolutionaryscale.ai
Does a similar job
all alternatives →
I built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
An open-source implementation of AlphaFold32024 · github.com · ▲314Hi HN - we’re the founders of Ligo Biosciences and are excited to share an open-source implementation of AlphaFold3, the frontier model for protein structure prediction. Google DeepMind and their new startup Isomorphic Labs, are expanding into drug discovery. They developed AlphaFold3 as their model to accelerate drug discovery and create demand from big pharma. They already signed Novartis and Eli Lilly for $3 billion - Google’s becoming a pharma company! (https://www.isomorphiclabs.com/articles/isomorphic-labs-kick...) AlphaFold3 is a biomolecular structure prediction…
Timber – Ollama for classical ML models, 336x faster than PythonMar 2026 · github.com · ▲207Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference. - kossisoroyce/timber
Model2vec – Lightning-fast Static Embeddings for RAG/Semantic Search2024 · github.com · ▲28We’ve recently open-sourced Model2vec, a method to distill sentence transformers into static embeddings that outperform all previous approaches by a large margin on MTEB. Our new models set a new state-of-the-art for static embeddings. Main features: - Our best model (potion-base-8M) has only 8M parameters, which is ~30mb on disk - Inference is ~500x faster than the distilled base model (bge-base), on a CPU - New models can be distilled in 30 seconds on a CPU without requiring a dataset - just a vocabulary - Numpy-only inference: The packaged can be install the package with minimal…
Model2vec-Rs – Fast Static Text Embeddings in Rust2025 · github.com · ▲60Hey HN! We’ve just open-sourced model2vec-rs, a Rust crate for loading and running Model2Vec static embedding models with zero Python dependency. This allows you to embed text at (very) high throughput; for example, in a Rust-based microservice or CLI tool. This can be used for semantic search, retrieval, RAG, or any other text embedding usecase. Main Features: - Rust-native inference: Load any Model2Vec model from Hugging Face or your local path with StaticModel::from_pretrained(...). - Tiny footprint: The crate itself is only ~1.7 mb, with embedding models between 7 and 30 mb. Performance:…
Explore large language models with 512MB of RAM2023 · github.com · ▲138Explore large language models in 512MB of RAM. Contribute to jncraton/languagemodels development by creating an account on GitHub.
More life & fun this month
the category →
A free city-building game in your browser. You are the mayor. You know what the city needs. Now get it past the zoning board, the neighbors, the appeals court and the next election.
Life & fun · 3d ago · permit.petercai.com
- IV
Life & fun · 16d ago · tanzaniaeducationproject.org
Turn a phone, tablet or TV into a sign. Type a message and it fills the screen: welcome signs, timers, Wi-Fi passwords and more. No app, no account, free.
Life & fun · 16d ago · bigwords.page
Play a free virtual guitar online with your keyboard or by touch. Slow songs down and see every chord, string and strum. Acoustic, classic, electric and bass.
Life & fun · 10d ago · guitoro.com
Carrier settings from iPhone, Pixel and Galaxy firmware, decoded and compared: APNs, VoLTE, 5G and Wi-Fi Calling per carrier, and what each build changed.
Life & fun · 14d ago · carrierexplode.com
Life & fun · 24d ago · space.bl2.net
Source: Show HN post ↗
