Llmfit
starred
Docker
Hundreds of models & providers. One command to find what runs on your hardware.
§01 · Projects
Projects.
Filament plugins, Laravel packages and open source starter kits actively maintained. All MIT, with releases for v3, v4 and v5 where applicable.
§02 · catalogue
Soup
starred
Docker
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Shimmy
starred
Docker
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Neutronstar
starred
Application
Giant MoE models on a single consumer GPU by streaming experts from SSD. CUDA fork of antirez/ds4: runs GLM-5.2 (743B), Tencent Hy3 (295B), and DeepSeek 4 Flash, with io_uring expert streaming, LFU host cache, cross-layer expert prefetch, and the first MTP speculative decoding for GLM-5.2.
§03 · contribute
Contribute, report issues, open PRs.
All packages have CI, Pest tests and open issues tagged good first issue.