#local-llm
Local LLMs on GitHub, October 19–25, 2026
In Local LLMs, 78 repos ranked the week of October 19 and gained 9,046 stars between them. Generated-Computers/Locals took #1, gaining 320 stars. The week brought 42 repos new to the topic's ranking, among them Magnvs7/Promethevs at #30.
The ranking as the week’s last hourly run left it, on October 26 at 00:00 UTC. It does not change.
- repos ranked
- 78
- stars gained
- 9,046
- ranked in #local-llm for the first time
- 42
The top 10
Ordered by stars gained over the seven days relative to each repo’s size, which is why a repo can rank above one that gained more.
- 1Generated-Computers/Locals Run many AI agents at once on your Mac, up to 3x faster.stars that week +320
- 2StartLuxLabs/StartLux-Decision Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.stars that week +838
- 3JMS1717/ming-voice Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linuxstars that week +285
- 4mw00/project-maya Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.stars that week +820
- 5Indras-Mirror/Xolotl Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM…stars that week +230
- 6simplexai-labs/PolyStrata Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.stars that week +258
- 8cobanov/PS5LM llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8stars that week +150
- 9ReDChicagOTypewriteR/ShotAI 面向可信局域网的本地 AI 工作台:基于 Ollama 提供对话、视觉理解、文档问答、知识库检索和 Windows 图片创作。stars that week +60
- 10ahtx/kindi Kindi 0.6.1: fast local LLM inference on low-cost GPUs and CPUs. DeepSeek-V4.1-Flash (552B) at 18.7 tok/s on one RTX 3060 12 GB with a dual-Xeon DDR4 server. Ternary Bonsai 2B-27B, AH-Nanbeige4.3-33B, Nemotron 3.5 Lightning 30B-A3B. NVIDIA from the Quadro K420 to the RTX 50 series, AMD Radeon…stars that week +60
12 repos of this ranking were removed since and are not shown: deleted from GitHub or taken out by Upstar’s review. Their ranks stay empty.
Ranks 11 to 30
- 11Mafdet-AI/mafdet +54 stars that week
- 12justxor/deepseek-local-guide-ru +48 stars that week
- 13maximpri/mlxtop +43 stars that week
- 14CSUNX233/Sparkle-Qwen27b-Kvmem-ninfer +43 stars that week
- 15nicorobinreal/llmspeed +45 stars that week
- 18Soulmate-Halo/heterogeneous-gpu-pd-lab +99 stars that week
- 19abhi245y/PS5LM-Plus +67 stars that week
- 20syv-ai/HyperQwen +152 stars that week
- 21MakazhanAlpamys/Soup +304 stars that week
- 22MAZHARMIK/python-ai-agent-ollama +30 stars that week
- 23StayLameBro/backburner +86 stars that week
- 24ddalcu/mlx-serve +118 stars that week
- 25ollama/ollama +1.1k stars that week
- 26peonist-ai/halogen-flash-server +81 stars that week
- 27hardenedlinux/SonicBoom +25 stars that week
- 28llamastash/llamastash +36 stars that week
- 30Magnvs7/Promethevs +24 stars that week
Show the other 40 repos
- 32magnitudedev/magnitude +182 stars that week
- 33shawnshekari/strixite +21 stars that week
- 35MagentaHokageType/ollama-windows-model-library-manager +21 stars that week
- 36ChaserMeadowlark/local-ai-api-endpoint-manager-windows +20 stars that week
- 38cactus-compute/cactus +223 stars that week
- 40AlexsJones/llmfit +306 stars that week
- 41nobodywho-ooo/nobodywho +62 stars that week
- 42AtomicBot-ai/atomic-agent +90 stars that week
- 43zhongkaifu/TensorSharp +34 stars that week
- 44ollaya-dev/ollaya +49 stars that week
- 45feder-cr/jev +39 stars that week
- 46Osmantic/ODS +114 stars that week
- 47drumih/turbo-fieldfare +109 stars that week
- 49XHToken/Spark-X2.6 +33 stars that week
- 51Mintplex-Labs/anything-llm +292 stars that week
- 52prabanta-dev/janas +23 stars that week
- 53jundot/omlx +157 stars that week
- 54AtomicBot-ai/Atomic-Chat +41 stars that week
- 55ml-explore/mlx-lm +82 stars that week
- 56mostlygeek/llama-swap +72 stars that week
- 57PrismML-Eng/Bonsai-demo +45 stars that week
- 59ggml-org/Llama-macOS +30 stars that week
- 60isair/jarvis +32 stars that week
- 61youssofal/MTPLX +35 stars that week
- 62vllm-project/vllm-metal +26 stars that week
- 63fikrikarim/parlor +27 stars that week
- 64andrew-waters/orchard +24 stars that week
- 65ikawrakow/ik_llama.cpp +33 stars that week
- 66raullenchai/Rapid-MLX +36 stars that week
- 67janhq/jan +114 stars that week
- 69chatboxai/chatbox +107 stars that week
- 70off-grid-ai/OGAM +29 stars that week
- 71mozilla-ai/llamafile +78 stars that week
- 72cactus-compute/engine +36 stars that week
- 73Luce-Org/lucebox +23 stars that week
- 74Andyyyy64/whichllm +30 stars that week
- 75osaurus-ai/osaurus +30 stars that week
- 76Neywa-Labs/mlx-vlm +21 stars that week
- 77n4ze3m/page-assist +24 stars that week
- 78oobabooga/textgen +22 stars that week