Back to feed
Dev.to
Dev.to
5/11/2026
Tracking my cardio with OpenClaw and Gemma 4

Tracking my cardio with OpenClaw and Gemma 4

Short summary

Developer benchmarks Google's Gemma 4 local models (e2b vs e4b) on a Mac running OpenClaw for cardio tracking. Provides detailed performance metrics, setup checklist, and documents trade-offs between model size, speed, and offline privacy.

  • •e4b (4B) model benchmarked at 55 tokens/sec vs e2b (2B) at 409 tokens/sec with detailed eval metrics
  • •Built custom OpenClaw skill that logs 48 runs and enables natural language queries over historical data
  • •Prioritized privacy and cost (no API calls) over frontier model capabilities for local inference

Generated with AI, which can make mistakes.

#ai-tools#open-source#ai-agents
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

Building a Travel App with Gemma 4: Local Inference Without Cloud Costs
Dev.to
The original title is "LLMs on Consumer Hardware — Part 1: The Stack and First Benchmarks"
Dev.to
The original title is: "7.5B Gemma-4-e4b outscored 24B Devstral on a 56-task local coding benchmark"
Dev.to
Benchmarking Gemini 2.5 Flash vs 3.1 Flash-Lite vs Gemma 4 with LLM judge (Claude Fable 5)
Dev.to