AINewsnow

Qwen3.8 27B Measured on an RTX 5090 — and Why vLLM Didn't Work

Introduction Qwen3.8 27B came out, so I put it on my RTX 5090 (32GB). How it did on multi-step agent work is in Only the Design of My Eval Harness Survived ; this post is the numbers and the walls I hit along the way. On ollama, generation came out roughly twice as fast as the previous generation.…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-11-03 15:37 · DEV Community — Machine Learning
    Qwen3.8 27B Measured on an RTX 5090 — and Why vLLM Didn't Work

More stories

  1. OpenAI launches Grid Protectors Program to cut data center power use during grid strain — OpenAI News
  2. OpenAI hires former Army Secretary Dan Driscoll as senior counselor for national security — OpenAI News
  3. Security flaw found in Claude Code extension listed on Cursor's marketplace — Runway Research
  4. OpenAI raises bug bounty rewards and plans new security sprint with outside researchers — OpenAI News
  5. OpenAI seeks to rebrand data centers as 'compute campuses' amid growing local backlash — Techmeme
  6. Anthropic launches Message Threads in public beta, cutting agent request payloads from 800 KB to 1.8 KB — Anthropic (X)
  7. UK cyber chief warns AI-powered malware likely to hit critical infrastructure by 2028 — The Guardian AI
  8. AI Is Changing How Semiconductor Fabs Work — and Engineers Are Moving Faster Because of It — NVIDIA Blog

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