AINewsnow

Qwen3.8-27B on One RTX 3090 vs Two: +20% Decode, +14% Cold Prefill, and 3x on Cached Prompts

This story is from 2026-09-23. It is preserved in the archive; the latest stories are on the live feed.

TL;DR: Qwen3.8-27B — the dense 27.8B that dropped on August 14 — fits on a single RTX 3090 at W4A16 and decodes at ~125–155 tokens/sec . Splitting it across two cards with tensor parallelism buys roughly 20% more decode (noisy: +13% in one run, +22% in the next) and 14% faster prefill on average on…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-09-23 03:27 · DEV Community — AI
    Qwen3.8-27B on One RTX 3090 vs Two: +20% Decode, +14% Cold Prefill, and 3x on Cached Prompts

More stories

  1. GPT-6 Sol and Luna now available on AI Gateway — Vercel Blog
  2. Alibaba Unveils New AI Chip, Outlines Plan for Larger Model — Wall Street Journal Technology
  3. Anthropic launches Claude Opus 5.5 with stricter safeguards for cybersecurity — The Verge AI
  4. No Shirt, No Shoes, No Service: Amazon Blocks Meta’s Muse AI From Shopping — CNET AI
  5. Moonshot’s Kimi K3 lands on Amazon in key test for Chinese open-source AI revenue — South China Morning Post Tech
  6. How Benchling secured multi-tenant AI agents with Amazon Bedrock AgentCore — AWS Machine Learning Blog
  7. Trump says AI will be renamed 'super intelligence' in all US documents — The Hill Technology
  8. NVIDIA Isaac ROS 5.0 Advances Agentic, Open Source Robotics Development — NVIDIA Blog

Get the daily brief of stories like this at 6:30 every morning →