🌐 US-Proxy
class="sans-serif-article-body default-header" data-user-status="logged-out" data-is-root-subforem="false" data-subforem-id="1" data-side-nav-visible="true" data-community-name="DEV Community" data-subscription-icon="https://assets.dev.to/assets/subscription-icon-805dfa7ac7dd660f07ed8d654877270825b07a92a03841aa99a1093bd00431b2.png" data-community-leader-icon="https://assets.dev.to/assets/community-leader-icon-b72c9e74eff54916e5c46c962f47ba40c9f611a71f8b157511f9613f69c0001b.svg" data-locale="en" data-honeybadger-key="hbp_nqu4Y66HuEKlD6YRGssZuRQnPOjDm50J8Zkr" data-deployed-at="2026-10-19T21:58:30Z" data-latest-commit-id="389a49ccbfb3c0ade8aa178549e34e6a2d931179" data-ga-tracking="UA-71991109-1" data-cookie-banner-user-context="logged_out_only" data-cookie-banner-platform-context="off" data-algolia-id="PRSOBFP46H" data-algolia-search-key="9aa7d31610cba78851c9b1f63776a9dd" data-algolia-display="true" data-dynamic-url-component="bmar11" data-ga4-tracking-id="G-TYEM8Y3JN3" data-global-feature-flags-enabled="data_update_scripts onboarding_newsletter_content schedule_articles moderator_role display_ad_tags replace_unicorn_with_jump_to_comments article_id_adjusted_weight cloudflare_preferred_for_hosted_images multiple_reactions subscriber_icon ab_experiment_feed_strategy use_stories_endpoint digest_subject_testing digest_results_count_testing consistent_rendering discover_and_following_tabs hero_billboard onboarding_drip_emails algolia_frontend hide_onboarding_task_card optimize_article_tag_query dev_core_user_sync personalized_email_digests customerio_email_delivery community_favorites" data-style-fingerprint="c939ca9c3f">

DEV Community

Google Developer Experts

Organization Settings Admin

The official place for discovering GDE-created content and exploring how experts leverage Google technologies.

Joined Joined on 
Can a 26B MoE Run on an 8 GB GPU? Gemma 4 26B A4B on an RTX 3050
xbill profile

Can a 26B MoE Run on an 8 GB GPU? Gemma 4 26B A4B on an RTX 3050

#gemma #llamacpp #cuda #benchmarking
6
Comments
11 min read
How Much Context Fits Beside a 12B on an 8 GB GPU? Gemma 4 12B's Context Cache on an RTX 3050
xbill profile

How Much Context Fits Beside a 12B on an 8 GB GPU? Gemma 4 12B's Context Cache on an RTX 3050

#gemma #llamacpp #cuda #benchmarking
1
Comments
9 min read
Stress-Testing Gemini 4 Argon: Building a 3D Flutter Kart Game in 15 Prompts with Zero Assets
leehack profile

Stress-Testing Gemini 4 Argon: Building a 3D Flutter Kart Game in 15 Prompts with Zero Assets

#flutter #ai #webassembly #gamedev
11
Comments 1
6 min read
Automated GitHub Code Reviews Using Google Gemini Update: Enterprise-Ready, Multimodal, and Battle-Hardened
dazbo profile

Automated GitHub Code Reviews Using Google Gemini Update: Enterprise-Ready, Multimodal, and Battle-Hardened

#githubactions #pullrequest #cicdpipeline #googlegemini
Comments
24 min read
Comparing Qwen and Gemma on the Low End: Qwen Is Faster Without Drafting, Gemma Has Better Quality
xbill profile

Comparing Qwen and Gemma on the Low End: Qwen Is Faster Without Drafting, Gemma Has Better Quality

#gemma #qwen #llamacpp #cuda
14
Comments
13 min read
Can a QAT 12B Fit an 8 GB GPU? Gemma 4 12B on an RTX 3050
xbill profile

Can a QAT 12B Fit an 8 GB GPU? Gemma 4 12B on an RTX 3050

#gemma #llamacpp #cuda #benchmarking
7
Comments
15 min read
[Agent Platform in Action (1)] Building a LINE AI Business Card Master with Go and Google ADK 2.0: From Fan-Out Parallel Retrieval to HITL Pause
evanlin profile

[Agent Platform in Action (1)] Building a LINE AI Business Card Master with Go and Google ADK 2.0: From Fan-Out Parallel Retrieval to HITL Pause

#agents #ai #architecture #go
Comments
14 min read
Google Workspace Studio Tutorial: Batch Lead Outreach with the "Repeat for each" Loop
aryanirani123 profile

Google Workspace Studio Tutorial: Batch Lead Outreach with the "Repeat for each" Loop

#ai #automation #productivity #tutorial
8
Comments
10 min read
loading...