Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

·Hacker News··

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input. - Niko1221/Strata

Read full article →

Related Articles

Federal judge calls Flock 'indiscriminate mass surveillance'
sbulaev · Hacker News · 16h ago
Kolibri: A Sovereign Open-Weight Model
bastitx · Hacker News · 1d ago
Pi 1.0
sergiotapia · Hacker News · 2d ago
Updates to Full Disk Access in macOS
notfirstpost · Hacker News · 1d ago
Court agrees with EFF: Utah's VPN law demands a technical impossibility
hn_acker · Hacker News · 2d ago