Sleeping Inference Benchmarking Results Phi-4 (8000 Tokens) 📊 Generate detailed latency metrics for model benchmarks
Running Inference Benchmarking Results Phi-4 (200 Tokens) 📊 Visualize benchmark results for model performance
textgeflecht/Qwen2.5-Coder-32B-Instruct-FP8-dynamic Text Generation • 33B • Updated Jun 12, 2025 • 9
textgeflecht/Devstral-Small-2505-FP8-llmcompressor Text Generation • 24B • Updated May 25, 2025 • 7
