---
title: "#gemma articles | Hashnode"
description: "Explore 52 articles tagged #gemma on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/gemma"
---

Tag

# #gemma

52 posts · 0 followers

[Abdus Salam](https://hashnode.com/@aheadkit) · [5d ago](https://hashnode.com/posts/gemma-4-e2b-on-four-accelerators-which-serving-engine-wins-where/6af7b0f40cc65806c4696ec1)

### [Gemma 4 E2B on Four Accelerators: Which Serving Engine Wins Where](https://aheadkit.hashnode.dev/gemma-4-e2b-on-four-accelerators-which-serving-engine-wins-where?utm_source=hashnode&utm_medium=feed)

The same small model, Gemma 4 E2B, served by six engines on four chips: an 8 GB RTX 3050 in a desktop, a Tesla T4 on Compute Engine, an NVIDIA L4 in an EC2 G6, and one Cloud TPU v5e chip. Each platfor

10 min read · [aheadkit.hashnode.dev](https://aheadkit.hashnode.dev/gemma-4-e2b-on-four-accelerators-which-serving-engine-wins-where?utm_source=hashnode&utm_medium=feed)

[Fotie M. Constant](https://hashnode.com/@fotiecodes) · [Sep 23](https://hashnode.com/posts/project-turaco-is-finally-showing-promise/6ab3cb6a344682413e550c4d)

### [Project Turaco Is Finally Showing Promise](https://blog.fotiecodes.com/project-turaco-is-finally-showing-promise?utm_source=hashnode&utm_medium=feed)

For more than a year, I have been trying to answer one question: can we build a machine translation model that translates English into natural Cameroon Pidgin without sounding like it is guessing? Tha

3 min read · [blog.fotiecodes.com](https://blog.fotiecodes.com/project-turaco-is-finally-showing-promise?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/project-turaco-is-finally-showing-promise/6ab3cb6a344682413e550c4d)

[Jaikishan Nayak](https://hashnode.com/@JaikishanN) · [Aug 26](https://hashnode.com/posts/building-ai-agents-with-google-cloud-my-journey-through-three-tracks/6a8ec3e850653d2bb2522460)

### [Building AI Agents with Google Cloud: My Journey Through Three Tracks](https://dsadigest.hashnode.dev/building-ai-agents-with-google-cloud-my-journey-through-three-tracks?utm_source=hashnode&utm_medium=feed)

My journey building and deploying three AI agents with Google Cloud, Cloud Run, Gemini, and Gemma through three hands-on tracks.

7 min read · [dsadigest.hashnode.dev](https://dsadigest.hashnode.dev/building-ai-agents-with-google-cloud-my-journey-through-three-tracks?utm_source=hashnode&utm_medium=feed)

[circuitrocks](https://hashnode.com/@circuitrocks) · [Aug 26](https://hashnode.com/posts/litert-on-raspberry-pi-5-run-gemma-and-vision-models-locally/6a8f637bb388d756e87da989)

### [LiteRT on Raspberry Pi 5: Run Gemma and Vision Models Locally](https://circuitrocks.hashnode.dev/litert-on-raspberry-pi-5-run-gemma-and-vision-models-locally?utm_source=hashnode&utm_medium=feed)

LiteRT Raspberry Pi 5: Google's LiteRT CLI puts Gemma and EfficientNet on a Raspberry Pi 5 with three commands.

2 min read · [circuitrocks.hashnode.dev](https://circuitrocks.hashnode.dev/litert-on-raspberry-pi-5-run-gemma-and-vision-models-locally?utm_source=hashnode&utm_medium=feed)

[circuitrocks](https://hashnode.com/@circuitrocks) · [Aug 16](https://hashnode.com/posts/run-gemma-ai-offline-on-a-raspberry-pi-5-with-googles-litert/6a81374e18fc676a9ec24164)

### [Run Gemma AI Offline on a Raspberry Pi 5 with Google's LiteRT](https://circuitrocks.hashnode.dev/run-gemma-ai-offline-on-a-raspberry-pi-5-with-googles-litert?utm_source=hashnode&utm_medium=feed)

Run Gemma AI Offline: Google's LiteRT runs Gemma models on a Raspberry Pi 5 at 99 tokens/sec prefill in 1432 MB of RAM, with no cloud and no API key…

3 min read · [circuitrocks.hashnode.dev](https://circuitrocks.hashnode.dev/run-gemma-ai-offline-on-a-raspberry-pi-5-with-googles-litert?utm_source=hashnode&utm_medium=feed)

[Chukwuemeka Aladimma](https://hashnode.com/@Acel) · [Aug 14](https://hashnode.com/posts/lm-studio-on-windows-wsl2-for-development-the-setup-guide-i-wish-i-had/6a7ec1a8ed78d85de3331eae)

### [LM Studio on Windows, WSL2 for Development: The Setup Guide I Wish I Had](https://blog.acel.dev/lm-studio-on-windows-wsl2-for-development-the-setup-guide-i-wish-i-had?utm_source=hashnode&utm_medium=feed)

Connecting Gemma to Python applications when your model runs on Windows but your development environment lives in WSL2

9 min read · [blog.acel.dev](https://blog.acel.dev/lm-studio-on-windows-wsl2-for-development-the-setup-guide-i-wish-i-had?utm_source=hashnode&utm_medium=feed)

[Pavel](https://hashnode.com/@keenthinker) · [Aug 9](https://hashnode.com/posts/running-ollama-and-translategemma-on-windows-server-2022-what-i-learned/6a7855acd72b3cbbf201c74d)

### [Running Ollama and TranslateGemma on Windows Server 2022: what I learned](https://blog.keenthinker.com/running-ollama-and-translategemma-on-windows-server-2022-what-i-learned?utm_source=hashnode&utm_medium=feed)

What I learned when moving a local Ollama and TranslateGemma setup from my personal computer to a virtual Windows Server 2022 environment - including Task Scheduler, CORS, networking, permissions and memory management.

14 min read · [blog.keenthinker.com](https://blog.keenthinker.com/running-ollama-and-translategemma-on-windows-server-2022-what-i-learned?utm_source=hashnode&utm_medium=feed)

[Yuki Furuta](https://hashnode.com/@yukifuruta) · [Jul 22](https://hashnode.com/posts/running-edge-llms-on-a-raspberry-pi/6a60db8bdde79fad26351170)

### [Running Edge LLMs on a Raspberry Pi](https://blog.yukifuruta.com/running-edge-llms-on-a-raspberry-pi?utm_source=hashnode&utm_medium=feed)

Running Edge LLMs on a Raspberry Pi 5 with 8GB RAM: Comparing Gemma 4 and Qwen with LiteRT-LM and llama.cpp

24 min read · [blog.yukifuruta.com](https://blog.yukifuruta.com/running-edge-llms-on-a-raspberry-pi?utm_source=hashnode&utm_medium=feed)

[Nakonakokawaii](https://hashnode.com/@nakokawaii) · [Jul 13](https://hashnode.com/posts/gemma-4-12b-on-a-16gb-laptop-a-privacy-first-local-ai-business-playbook/6a54ae5e67763ef89e6abc48)

### [Gemma 4 12B on a 16GB Laptop: A Privacy-First Local AI Business Playbook](https://ai-change-brief.hashnode.dev/gemma-4-12b-on-a-16gb-laptop-a-privacy-first-local-ai-business-playbook?utm_source=hashnode&utm_medium=feed)

Google’s mid-sized multimodal open model creates a credible path to on-device services, but the winning offer is controlled workflow design—not a vagu

5 min read · [ai-change-brief.hashnode.dev](https://ai-change-brief.hashnode.dev/gemma-4-12b-on-a-16gb-laptop-a-privacy-first-local-ai-business-playbook?utm_source=hashnode&utm_medium=feed)

[Chris Sheridan](https://hashnode.com/@auto-majicly) · [Jul 6](https://hashnode.com/posts/the-bug-that-made-my-pentesting-agent-give-up/6a4c10e47b6d490fc0580230)

### [The Bug That Made My Pentesting Agent Give Up](https://halosecurityhasnodedev.hashnode.dev/the-bug-that-made-my-pentesting-agent-give-up?utm_source=hashnode&utm_medium=feed)

I’ve been building Halo, an autonomous pentesting agent powered by a local LLM (Gemma 4 12B, abliterated, running via LM Studio). Last week I found a bug in it that taught me more about state management in agentic systems than anything else I’ve hit so far.

3 min read · [halosecurityhasnodedev.hashnode.dev](https://halosecurityhasnodedev.hashnode.dev/the-bug-that-made-my-pentesting-agent-give-up?utm_source=hashnode&utm_medium=feed)

[5](https://hashnode.com/posts/the-bug-that-made-my-pentesting-agent-give-up/6a4c10e47b6d490fc0580230)
