# microsoft/BitNet

> Official inference framework for 1-bit LLMs (BitNet b1.58) with optimized kernels for CPU and GPU. Runs ternary models fast and losslessly, including a 100B model on a single CPU.

- Magnitude: 1.9 out of 10 — Steady
- Stars: 41,445 total · +8 stars measured 2026-11-02, 00:11–23:09 UTC
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: MIT · Created: 2024-08-05 · Last push: 2026-07-27
- GitHub: https://github.com/microsoft/BitNet · Page: https://gitnova.dev/en/r/microsoft/BitNet

## Useful for

- Run BitNet-b1.58-2B-4T locally on CPU for chat without a GPU
- Speed up 1-bit embedding model inference on x86 with I2_S kernels
- Deploy a 1.58-bit LLM on an edge device with low energy use

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 00:11–23:09: 41437 → 41445 stars (+8). This is the change over that interval.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,864
- Issues and pull requests: 599
- Watchers: 362
- Average over the last week: 32 per day
- Usual pace: 27 per day
- Stars in the last hour (measured): 1

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 3, 7, 9, 6, 4, 4, 219, 124, 317, 119, 24, 12, 7, 8, 17, 11, 13, 7, 5, 9, 4, 8, 9, 24, 16, 71, 35, 43, 24, 8

## Magnitude by day, last 14 days

10-18 1.3, 10-19 1.6, 10-20 1.3, 10-21 1.3, 10-22 1.1, 10-23 1.1, 10-24 1.2, 10-25 0.9, 10-28 1.8, 10-29 2.4, 10-30 3.1, 10-31 2.8, 11-01 2.7, 11-02 2.2

## More in this category

1. **karpathy/nanochat** — 6.7 · Breakout · Language models · Python · +250 stars measured 2026-11-02, 11:38–23:02 UTC
   A minimal experimental harness for training LLMs on a single GPU node, covering tokenization, pretraining, finetuning, evaluation and inference. It lets you train a GPT-2-capability model for about $48 and chat with it via CLI.
   Full card: https://gitnova.dev/en/r/karpathy/nanochat.md
2. **togg53192-cmd/jailbreaks** — 5.7 · Peaking · Language models · +696 stars measured 2026-11-02, 00:07–23:03 UTC
   A collection of 31 system prompts, persona locks, and AGENTS.md files for 25+ models (Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Gemma, GPT-OSS). Intended for research on how instruction hierarchies and policy overrides affect model…
   Full card: https://gitnova.dev/en/r/togg53192-cmd/jailbreaks.md
3. **FlashML-org/FreeToken** — 5.6 · Breakout · Language models · Python · +625 stars measured 2026-11-02, 00:07–23:03 UTC
   A Mixture-of-Experts inference engine for running frontier-scale open-weight MoE models (290B+) on consumer hardware — GPUs, CPUs, and host memory. Aimed at users who want to run frontier models locally.
   Full card: https://gitnova.dev/en/r/FlashML-org/FreeToken.md
4. **p-e-w/heretic** — 5.3 · Breakout · Language models · Python · +500 stars measured 2026-11-02, 00:09–23:03 UTC
   A tool for fully automatic removal of censorship (safety alignment) from transformer-based language models using directional ablation and Optuna-based parameter optimization.
   Full card: https://gitnova.dev/en/r/p-e-w/heretic.md
5. **JustVugg/colibri** — 5.1 · Breakout · Language models · C · +703 stars measured 2026-11-02, 00:08–23:03 UTC
   A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.
   Full card: https://gitnova.dev/en/r/JustVugg/colibri.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 23:16 UTC, updated every 30 minutes.