Article
Nacrith: How a 135M Language Model Became the Best Text Compressor We've Tested
•
1
Roberto Tacconelli PRO
robtacconelli
AI & ML interests
None yet
Recent Activity
new activity
about 5 hours ago
robtacconelli/smollm2-135M-GGUF:Improve dataset card: add metadata, links and usage information updated
a dataset about 5 hours ago
robtacconelli/smollm2-135M-GGUF reacted
to
their post with 🔥 about 7 hours ago
🏆 Nacrith: a 135M model that out-compresses everything on natural language
What if a tiny LM could compress english text better than _every_ compressor out there — classical or neural, small or large?
Nacrith pairs SmolLM2-135M with an ensemble of online predictors and high-precision arithmetic coding.
What's inside
The standard LLM+arithmetic coding approach wastes ~75% of CDF precision on large vocabularies. Our CDF-24 fix alone recovers 0.5 bpb. On top: a token N-gram that skips the GPU on predictable tokens, an adaptive bias head, llama.cpp backend (7× faster than PyTorch), multi-GPU parallel compression, and a binary file format (NC06) — the first LLM-based binary compressor we know of.
Runs on a GTX 1050 Ti. ~500 MB weights, ~1.2 GB VRAM per worker.
💻 Code: https://github.com/robtacconelli/Nacrith-GPU
⭐ Space: https://huggingface.co/spaces/robtacconelli/Nacrith-GPU
📄 Paper: https://huggingface.co/papers/2602.19626
Try it, break it, share your results — all feedback welcome. ⭐ on the repo appreciated!
Results across all systems we tested:
- alice29.txt → 0.918 bpb (−44% vs CMIX, −20% vs ts_zip) — below the 2nd-order Shannon entropy bound
- enwik8 (100 MB) → 0.9389 bpb (−8% vs FineZip/LLMZip's 8B model, −15% vs ts_zip)
- Unseen text → 0.723 bpb on a doc published after training cutoff — no memorization, 26% better than FineZip/LLMZip on the same model
SmolLM2-135M by https://huggingface.co/HuggingFaceTB Organizations
None yet
published an
article about 24 hours ago