Local AI

Peak · emerged March 2023 · high July 2026 · -19% on the month before · 44 mentions on Trending in 14 days

Running language and image models on your own laptop, phone or server instead of a cloud API. Named by Georgi Gerganov: llama.cpp: LLaMA inference in plain C/C++ (Mar 10, 2023). Also called Local LLMs, On-device AI, Self-hosted AI, Running models locally.

Index 0 to 100, monthly

Signals

Signal	Value	Reads as
Hacker News stories, last 12 months813 stories, +185% on the 12 months before	813 stories, +185% on the 12 months before	Adoption
arXiv papers, last 12 months237 papers, +81% on the 12 months before	237 papers, +81% on the 12 months before	Adoption
Wikipedia views, August 202610,075, +73% on a year before	10,075, +73% on a year before	Adoption
Product releases naming it1 since Sep 1, 2025	1 since Sep 1, 2025	Adoption
GitHub repositories27,725	27,725	Adoption

Trending terms

Term	Last day	Days	PeakPeak score
MLXAI product2 days, last Sep 19 6 days ago	Sep 196 days ago	2	25
llama.cppAI product2 days, last Sep 14 11 days ago	Sep 1411 days ago	2	25
DGX SparkHardware2 days, last Sep 4 3 weeks ago	Sep 43 weeks ago	2	28
LM StudioAI product1 day, last Sep 3 3 weeks ago	Sep 33 weeks ago	1	25
OllamaAI product2 days, last Sep 3 3 weeks ago	Sep 33 weeks ago	2	25

Companies

Name	Mentions
Ollama	1

Releases

1 release since Sep 1, 2025

Name	Date
Ollama 0.34.2Ollama · Sep 17, 2026 8 days ago	Sep 17, 20268 days ago

Models

Name
Gemma 3 4bGoogle
Gemma 3 1bGoogle
Llama 3.2 3bMeta
Llama 3.2 1bMeta
Qwen3 8bAlibaba
Qwen3-Embedding-8B (Qwen)Alibaba

GitHub projects

27,725 repositories

Name	Created	Stars
nomic-ai/gpt4allGPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. · Mar 27, 2023 3 years ago	Mar 27, 20233 years ago	77,384
oobabooga/textgenOpen-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private. · Dec 21, 2022 3 years ago	Dec 21, 20223 years ago	47,706
khoj-ai/khojYour AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Tur · Aug 16, 2021 5 years ago	Aug 16, 20215 years ago	37,493
intel/ipex-llmAccelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, et · Aug 29, 2016 10 years ago	Aug 29, 201610 years ago	8,853
Andyyyy64/whichllmFind the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One · Mar 4, 2026 6 months ago	Mar 4, 20266 months ago	6,682
pguso/ai-agents-from-scratchDemystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct pattern · Oct 23, 2025 11 months ago	Oct 23, 202511 months ago	4,809

Movement	Stage
Small language modelsCompact models, a few billion parameters or less, trained to be good enough and cheap to run anywhere.	Peak
Open-weight modelsModels whose trained weights anyone can download, run and fine-tune: Llama, Qwen, DeepSeek, Mistral and more.	Rising
Inference chipsAccelerators built to serve models cheaply and fast rather than to train them: TPUs, LPUs, wafer-scale and custom silicon.	Peak

History

Date	What changed
Sep 24, 2026	Tracking started: emerged March 2023, peak, 4 other names recorded

Sources: Curve: Hacker News story titles, Wikipedia pageviews and arXiv papers by month, refreshed Sep 24, 2026. Related entities from the fru.dev sites' public APIs, matched by name. How stages work.