1.StartLuxLabs / 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.
+1,573 stars
from 59 · score 7.36
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
9 repositories by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
2.cobanov / PS5LM
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
+764 stars
from 21 · score 6.64
3.sgaofen / humanizer-local-model
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts
+691 stars
from 3 · score 6.54
4.Soulmate-Halo / heterogeneous-gpu-pd-lab
使用稠密算力卡对稀疏大显存主机进行加速，主机包括 AI Max+ 395、M3 512G、DGX Spark 等。
+450 stars
from 601 · score 6.11
5.mozilla-ai / llamafile
Distribute and run LLMs with a single file.
+424 stars
from 26,118 · score 6.05
6.off-grid-ai / OGAM
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
+122 stars
from 3,194 · score 4.81
7.defilantech / LLMKube
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
+24 stars
from 225 · score 3.22
8.SciSharp / LLamaSharp
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.
+21 stars
from 3,802 · score 3.09
9.getumbrel / llama-gpt
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
+10 stars
from 10,914 · score 2.40