📊 Benchmarks Overview

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

• LLaMA3
• Gemma3
• Gemma4
• Qwen2.5
• Qwen3
• Qwen3.5
• Qwen3.6
• Qwen3.8
• gpt-oss
• Decision 3.0 (d3)
• LiquidAI/LFM2
• LiquidAI/LFM3
• Microsoft/Phi4
• Nanbeige4.1
• SmolVLA
• Hy-MT2
• MiniCPM-V 4.7
• Nemotron Bolt
• Nemotron Bolt DFlash
• Flash Models

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