Pipette by Liquid AI
About

On-device model benchmark leaderboard

An open-source platform for the large-scale benchmarking of foundation models on devices.

Models benchmarked

  • LiquidAI/LFM2.5-1.2B-Instruct-GGUF
  • LiquidAI/LFM2.5-2.6B-GGUF
  • LiquidAI/LFM2.5-230M-GGUF
  • LiquidAI/LFM2.5-350M-GGUF
  • LiquidAI/LFM2.5-8B-A1B-GGUF
  • bartowski/Ling-3.0-tiny-GGUF
  • bartowski/Nanbeige_Nanbeige4.2-3B-GGUF
  • bartowski/Ornith-1.5-9B-GGUF
  • bartowski/ai9stars_G9v3-3B-GGUF
  • bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF
  • ibm-granite/granite-4.0-350m-GGUF
  • ibm-granite/granite-4.0-h-1b-GGUF
  • ibm-granite/granite-4.0-h-350m-GGUF
  • ibm-granite/granite-4.0-h-micro-GGUF
  • ibm-granite/granite-4.1-8b-GGUF
  • mistralai/Ministral-3-3B-Instruct-2512-GGUF
  • mistralai/Ministral-3-8B-Instruct-2512-GGUF
  • mradermacher/Qwen3.5-27B-i1-GGUF
  • mradermacher/Qwen3.6-27B-i1-GGUF
  • openbmb/MiniCPM5-1B-GGUF
  • prism-ml/Bonsai-27B-gguf
  • prism-ml/Ternary-Bonsai-27B-gguf
  • tiiuae/Falcon-H1R-7B-GGUF
  • unsloth/Llama-3.2-1B-Instruct-GGUF
  • unsloth/Llama-3.2-3B-Instruct-GGUF
  • unsloth/Ministral-3-3B-Instruct-2512-GGUF
  • unsloth/Olmo-3-7B-Think-GGUF
  • unsloth/Ornith-1.0-9B-GGUF
  • unsloth/Qwen3.5-0.8B-GGUF
  • unsloth/Qwen3.5-2B-GGUF
  • unsloth/Qwen3.5-4B-GGUF
  • unsloth/Qwen3.5-9B-GGUF
  • unsloth/gemma-4-12b-it-GGUF
  • unsloth/gemma-4-E2B-it-GGUF
  • unsloth/gemma-4-E4B-it-GGUF

Devices benchmarked

  • Galaxy S26 Ultra
  • MacBook Pro
  • iPhone 17 Pro