Yhn HealthFitness first seen 3 d ago, last 50 min ago, peak #6

Qwen3.8 hits 255 tokens per second on one RTX 5090

Original: Running Qwen3.8 at 255 tok/s on a single 5090

A developer reports running the Qwen3.8 language model at 255 tokens per second on a single Nvidia RTX 5090 graphics card, a notably high inference speed for consumer hardware. The claim has drawn attention on Hacker News, where readers are discussing the performance figure and what it says about running capable AI models locally without expensive server equipment.

Why now: High-speed local inference of a modern LLM on a single consumer GPU is a striking benchmark that AI enthusiasts want to verify and replicate.

Qwen3.8Nvidia RTX 5090Hacker NewsMesh Applied

Open on hn →

Rank over time, top of the chart is #1. 4 snapshots from 4 h ago to 50 min ago.

Evidence

• Running Qwen3.8 at 255 tok/s on a single 5090 · Ir0n · 15

API: https://socialmediatrends-api.osmike.com/v1/trends/2164021