Speed and quality benchmarks for quantized LLMs on NVIDIA RTX 5090 32GB. Data, tooling, and results.
🏗️ Building on HF
witcheer
witcheer
AI & ML interests
Local AI Maxxing.
Recent Activity
updated a dataset about 2 hours ago
witcheer/rtx-5090-benchmarks liked a model 4 days ago
Qwen/Qwen3.8-27B updated a model 7 days ago
witcheer/gemma-3-27b-eagle3-drafterOrganizations
