G-B-KEVIN-ARJUN/runtime-inference

"Faster AI: Accelerating Qwen 2.5 from 7 t/s to 82 t/s on a single RTX 4060 using Llama.cpp and ONNX" a comparative analysis of LLM inference runtimes (PyTorch, ONNX, Llama.cpp) on consumer hardware. Benchmarking throughput, latency, and quantization trade-offs to optimize local deployment.

11
/ 100
Experimental
No License No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

Last pushed

Jan 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/G-B-KEVIN-ARJUN/runtime-inference"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.