gpu-benchmarks

Here are 8 public repositories matching this topic...

Benchmark results and performance data for the Intel Arc Pro B70 GPU (Xe2/Battlemage) - LLM inference, video generation, dual-GPU scaling.

sycl xe2 intel-gpu ai-inference intel-arc llama-cpp llm-inference battlemage gpu-benchmarks arc-pro-b70

aws benchmark hpc gpu cuda rdma efa rdma-benchmarks large-language-models llm cpp20-coroutine gpu-benchmarks

⚡ Compare AI models by Accuracy × Cost × Carbon — RTX 5090 benchmarks reveal 4-bit quantization wastes energy on small models

Run local LLMs on Intel Arc Pro B60 GPUs using vLLM and Docker. Includes configuration guides and deployment tools for Linux environments.

docker docker-compose transformers openai sycl xpu stable-diffusion openai-whisper llama-cpp vllm genai b50 openwebui gpt-oss-20b gpu-benchmarks intel-arc-b60

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).

What 4x GTX 1080 Ti still do in 2026 — measured benchmarks, design rationale, and field notes for running LLMs on hardware CUDA 13 dropped.

pascal cuda self-hosted homelab rag mixture-of-experts llama-cpp local-llm gpu-benchmarks gtx-1080-ti

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."