Benchmark results and performance data for the Intel Arc Pro B70 GPU (Xe2/Battlemage) - LLM inference, video generation, dual-GPU scaling.
⚡ Compare AI models by Accuracy × Cost × Carbon — RTX 5090 benchmarks reveal 4-bit quantization wastes energy on small models
Connectome-scale SNN simulation energy benchmarks — software ceiling analysis for Drosophila whole-brain on GPU
Optimal GPU, VRAM, and RAM configurations for running DeepSeek R1 locally (7B to 671B models).
Run local LLMs on Intel Arc Pro B60 GPUs using vLLM and Docker. Includes configuration guides and deployment tools for Linux environments.
Add a description, image, and links to the gpu-benchmarks topic page so that developers can more easily learn about it.
To associate your repository with the gpu-benchmarks topic, visit your repo's landing page and select "manage topics."