Repositories
41
Net stars gained, last 7 days
+14,987
Top-level Tag
Net stars gained each day, last 90 days
Peak days
- 1
Oct 4, 2026 +3,852 net stars (median day +1,359)
- Niko1221/Strata+2,883 (75%)
Created on Sep 24, 2026
- antirez/ds4+279 (7%)
- Edge0-AI/Edge0+222 (6%)
- 2
Oct 5, 2026 +3,464 net stars (median day +1,359)
- Niko1221/Strata+2,624 (76%)
Created on Sep 24, 2026
- Edge0-AI/Edge0+200 (6%)
- ggml-org/llama.cpp+115 (3%)
- 3
Oct 11, 2026 +3,034 net stars (median day +1,359)
- Niko1221/Strata+1,041 (34%)
- lyogavin/airllm+769 (25%)
- Edge0-AI/Edge0+208 (7%)
- 4
Oct 12, 2026 +3,292 net stars (median day +1,359)
- Niko1221/Strata+1,073 (33%)
- lyogavin/airllm+1,003 (30%)
- microsoft/BitNet+317 (10%)
- 5
Oct 29, 2026 +3,120 net stars (median day +1,359)
- Edge0-AI/Edge0+1,276 (41%)
Published v0.1.1 on Oct 29, 2026
- Niko1221/Strata+663 (21%)
Published v0.2.8 on Oct 29, 2026
- anonnerdfrenzy/survival-llm+162 (5%)
Published library-2026-10-28 on Oct 28, 2026 · Published v0.4.0 and v0.4.1 on Oct 29, 2026 · Created on Oct 24, 2026
A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occurred near the same day. They do not show why the stars came.
Largest
Most stars in total now.
- ollama/ollama186K
description:
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
readme:
The main goal of `llama.cpp` is to enable LLM (and VLM) inference with minimal setup and state-of-the-art performance on
description:
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX
readme:
GPT4All runs large language models (LLMs) privately on everyday desktops & laptops.
readme:
This repository is intended as a minimal example to load Llama 2 models and run inference.
readme:
This repository contains JAX example code for loading and running the Grok-1 open-weights model.
description:
Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
description:
Run frontier AI locally.
readme:
A desktop app for local LLMs. Open source, no telemetry.
- janhq/jan45K
readme:
Download and run LLMs (Llama, Gemma, Qwen, GPT-oss etc.) from HuggingFace
Newest Admissions
Entered the index by the rising rule, newest first.
description:
Run models larger than your RAM or VRAM by streaming MoE experts from SSD.
readme:
Avalon is a fork of llama.cpp built for one model,
description:
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
description:
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
description:
A free AI assistant and survival library that runs on your own computer, with no internet needed.
readme:
Slotstream is a fully native local AI engine for Apple Silicon Macs, written in Swift on Apple's MLX and Metal.
description:
runs open-weight models like Gemma and gpt-oss locally on Mac, Windows and Linux
readme:
AbliteratedOutTheBox is a fork of llama.cpp that gets any supported model to answer flagged harmful prompts
description:
MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU
readme:
a fully local, offline vision pipeline that lets text-only coding models see and read images
How a repository gets this Tag
An agent read the description, the GitHub topics, and the start of the README of each repository, and chose Tags only from the checked-in Tag list. For each Tag it quoted the text, and a code check kept the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories and does not say that one can replace another. A wrong Tag? Use "Report a problem with this page" on the page of the repository. Withheld Repositories are left out of all numbers on this page.