● LIVE

OpenAI releases GPT-5 APIIndia AI startup raises $120MBitcoin ETF hits record inflowsMeta Llama 4 benchmarks leakedOpenAI releases GPT-5 APIIndia AI startup raises $120MBitcoin ETF hits record inflowsMeta Llama 4 benchmarks leaked

📅 Fri, 5 Jun, 2026✈️ Telegram

AI & Tech News

✈️ Follow

☁️Cloud & DevOps

Running Brand-New Gemma 4 12B on an 8-Year-Old GTX 1080 Ti: Speed, 3 Gotchas, and Why Q8 Beat Q4 on My Own Field

TL;DR (Quick Answer) Gemma 4 12B just dropped, so I ran it on a GTX 1080 Ti (Pascal, 2017) to see what an 8-year-old card does with a 2026 model. Real numbers, and a few honest surprises: Speed: ~28 tok/s at Q4_K_M on a single 1080 Ti (~8 GB VRAM). The 12B fits one card, so the second GPU sits idle.

⚡

Key Insights

10 editorial insights.

AiFeed24 Team·⏱ 1 min read·Cloud & DevOps

✈️ Telegram 𝕏 Tweet WhatsApp

Deep Analysis

Multi-Source Intelligence

Tags:#cloud

Found this useful? Share it!

✈️ Telegram 𝕏 Tweet WhatsApp

Running Brand-New Gemma 4 12B on an 8-Year-Old GTX 1080 Ti: Speed, 3 Gotchas, and Why Q8 Beat Q4 on My Own Field

Deep Analysis

Multi-Source Intelligence

Related Stories

AI Coding Workflow 2026: What a YC Founder's Stack Taught Me About the Hard Parts [Guide]

Cloud Copilot Gets a Boost from Localized AI Processing

Creating Superior PDFs in Django Using Playwright Over Other Libraries

Edge Computing for IIoT: When to Process at the Source

Running Brand-New Gemma 4 12B on an 8-Year-Old GTX 1080 Ti: Speed, 3 Gotchas, and Why Q8 Beat Q4 on My Own Field

Deep Analysis

Multi-Source Intelligence

Related Stories

AI Coding Workflow 2026: What a YC Founder's Stack Taught Me About the Hard Parts [Guide]

Cloud Copilot Gets a Boost from Localized AI Processing

Creating Superior PDFs in Django Using Playwright Over Other Libraries

Edge Computing for IIoT: When to Process at the Source