📊 Benchmarks Overview

Browse detailed NPU benchmark results for each major model family supported by FastFlowLM:

• LLaMA 3.x
• Qwen 3
• Gemma 3
• gpt-oss
• LiquidAI/LFM2-1.2B

Each page includes decoding and prefill speed metrics (tokens per second) and notes about the test setup and hardware.