rtx-4080

Here are 4 public repositories matching this topic...

Provide tested tools and configs to run Qwen 3.5 GGUF models efficiently on a single 16GB NVIDIA GPU using llama.cpp locally.

benchmark nvidia vlm mixture-of-experts huggingface ai-inference llama-cpp local-llm local-ai qwen gguf llama-server rtx-5080 rtx-4080 vram-16gb

Complete Ubuntu 25.10 video playback setup with NVIDIA hardware acceleration (RTX 4080 SUPER)

ffmpeg ubuntu mpv nvidia video-playback vlc hardware-acceleration rtx-4080

RTX 4080 on macOS: GSP-RM boot, 4K display, compute, Vulkan (NVK), NVDEC and Metal from our own kexts. Made for fun.

macos metal nvidia hackintosh kext opencore gpu-driver rtx-4080

Evidence-backed, workload-conditioned autotuning for local LLM inference. Local-first control plane, G0–G8 validation, PyTorch · llama.cpp · vLLM.

performance-engineering cuda pytorch triton autotuning reproducibility mlops local-first llama-cpp vllm llm-inference gpu-benchmarking rtx-4080

To associate your repository with the rtx-4080 topic, visit your repo's landing page and select "manage topics."