BeRo1985/pasllm
PasLLM - LLM inference engine in Object Pascal (synced from my private work repository)
This project helps developers integrate specific Large Language Models (LLMs) into their Object Pascal applications. It takes pre-trained model weights (like Llama, Qwen, Phi) and allows them to be run efficiently on a CPU, even on resource-constrained systems. The output is text generated by the LLM, directly within the application. This is primarily for Pascal developers who need to embed local AI capabilities.
Use this if you are an Object Pascal developer building applications and need to integrate local, CPU-based inference for specific LLMs.
Not ideal if you require GPU acceleration, multi-modal capabilities, or support for the very latest LLM architectures like Mamba.
Stars
76
Forks
15
Language
Pascal
License
AGPL-3.0
Category
Last pushed
Jan 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/BeRo1985/pasllm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
ludwig-ai/ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
withcatai/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema...
mudler/LocalAI
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and...
zhudotexe/kani
kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)
SciSharp/LLamaSharp
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.