Trendingby GlyphLocal AI
Peak · emerged March 2023 · high July 2026 · +8% on the month before · 86 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
Hacker News stories, last 12 months938 stories, +194% on the 12 months before
arXiv papers, last 12 months266 papers, +73% on the 12 months before
Wikipedia views, October 202613,692, +180% on a year beforeProduct releases naming it7 since Feb 19, 2026GitHub repositories28,441| Signal | Reads as | |
|---|---|---|
| Hacker News stories, last 12 months938 stories, +194% on the 12 months before | 938 stories, +194% on the 12 months before | Adoption |
| arXiv papers, last 12 months266 papers, +73% on the 12 months before | 266 papers, +73% on the 12 months before | Adoption |
| Wikipedia views, October 202613,692, +180% on a year before | 13,692, +180% on a year before | Adoption |
| Product releases naming it7 since Feb 19, 2026 | 7 since Feb 19, 2026 | Adoption |
| GitHub repositories28,441 | 28,441 | Adoption |
Trending terms
MLXApple's machine learning framework for Apple silicon. 2 days in the top 20llama.cppAn open-source C++ engine for running models on ordinary hardware. 3 days in the top 20
DGX SparkNvidia's desktop AI computer. 1 day in the top 20
LM StudioA desktop app for running open-weight models locally. 1 day in the top 20
OllamaA tool for running open-weight models on your own computer. 1 day in the top 20
| Term | PeakPeak score | ||
|---|---|---|---|
| MLXApple's machine learning framework for Apple silicon.AI product2 days, last Sep 19 7 weeks ago | Sep 197 weeks ago | 2 | 19 |
| llama.cppAn open-source C++ engine for running models on ordinary hardware.AI product3 days, last Sep 14 8 weeks ago | Sep 148 weeks ago | 3 | 15 |
| Sep 42 months ago | 1 | 17 | |
| Sep 32 months ago | 1 | 15 | |
| Aug 282 months ago | 1 | 16 |
Companies
| Name | Mentions |
|---|---|
| 4 | |
| 1 |
Releases
7 releases since Feb 19, 2026| Name | |
|---|---|
| Oct 27, 202613 days ago | |
| Oct 9, 20264 weeks ago | |
| Oct 8, 20264 weeks ago | |
| Sep 17, 20267 weeks ago | |
| Sep 14, 20268 weeks ago | |
| Jul 8, 20264 months ago | |
| Mar 19, 20267 months ago |
Models
| Name |
|---|
| Gemma 3 4bGoogle |
| Llama 3.2 3bMeta |
| Qwen3 8bAlibaba |
| Qwen3-Embedding-8B (Qwen)Alibaba |
GitHub projects
28,441 repositoriesnomic-ai/gpt4allGPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.oobabooga/textgenOpen-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.khoj-ai/khojYour AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turintel/ipex-llmAccelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etAndyyyy64/whichllmFind the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. Onepguso/ai-agents-from-scratchDemystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct pattern
| Name | 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 | 77,389 |
| 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 | 47,721 |
| 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 | 37,562 |
| 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 | 8,852 |
| 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 8 months ago | Mar 4, 20268 months ago | 6,714 |
| 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 1 year ago | Oct 23, 20251 year ago | 4,825 |
Related movements
Small language modelsCompact models, a few billion parameters or less, trained to be good enough and cheap to run anywhere.Open-weight modelsModels whose trained weights anyone can download, run and fine-tune: Llama, Qwen, DeepSeek, Mistral and more.Inference chipsAccelerators built to serve models cheaply and fast rather than to train them: TPUs, LPUs, wafer-scale and custom silicon.
| Movement | Stage |
|---|---|
| Small language modelsCompact models, a few billion parameters or less, trained to be good enough and cheap to run anywhere. | Rising |
| 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
Tracking started: emerged March 2023, peak, 4 other names recorded
| 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 Nov 1, 2026. Related entities from the other Glyph Ibis sources' public APIs, matched by name. How stages work.