SamsungLabs/LittleBit
- Total stars
- 106
- Today · UTC
- +11since 16:51 UTC
More actions
Official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 2026)
Save to My finds to follow releases and star growth. Saved in this browser.
About the project
Official implementation of LittleBit (NeurIPS 2025) and LittleBit-2 (ICML 2026) — sub-1-bit LLM quantization methods that factorize weights into low-rank latent factors, binarize them, and restore magnitude with learned scales.
Useful for
- Compress Llama 2 7B to 1.0 or 0.1 bits per weight via QAT with SmoothSign
- Enable Joint-ITQ initialization with --use_itq to improve latent geometry
- Evaluate a checkpoint on wikitext2/c4 perplexity and zeroshot tasks via eval.py
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Star growth looks organic. Data as of October 8, 2026, 17:54 UTC.
The star-growth assessment does not verify whether the project is safe to run.
Stars per day
Bars show daily stars; the line is a moving average of the available history. Short histories do not yet establish a reliable usual pace. Red marks spike days.
Why it’s trending
- Star-counter measurements on 2026-10-08 (UTC), 16:51–17:49: 95 → 106 stars (+11). This is the change over that interval.
- Estimated end-of-day forecast: about +14 stars, using observed gains and the previous day.
- Hacker News: “Sub-1-Bit LLM Compression via Latent Factorization” — 43 points, 4 h ago.
- Recent forks include notable developers: @alexdolbun (708 followers), @danzeeeman (263 followers).
Three GitHub discoveries in each edition
What they do, why they are gaining interest, and what to check before using them.
Editions at 10:00, 16:00, 22:00 MSK.
Numbers
- Total stars
- 106
- Today
- +11 stars measured 2026-10-08, 16:51–17:49 UTC, ≈ 14 by evening
- Forks
- 16
- Issues and pull requests
- 20
- Watchers
- 3
- Language
- Python
- Created
- November 18, 2025
- Last push
- May 6, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Sub-1-Bit LLM Compression via Latent Factorization43 points, October 8, 2026
Spotted in
- October 8, 2026Spotted on Hacker News
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/SamsungLabs/LittleBit)