Qwen 3.8 27B just dropped and it's a beast.
52 on Artificial Analysis overall index, tied with DeepSeek V4 Flash. But on the agentic index, it's at 51, beating Luna, DeepSeek Flash, Muse Pro, and Terra. Running it on dual 3090s at 100-120 tokens per second. DeepSeek V4 Flash is
Ranking Every Single AI Model From Worst to Best
This summer had so many banger releases like Qwen 3.8, Kimi K3, Opus 5, Fable 5, GPT 5.6, Deepseek v4 and like 100 others... But which one is truly the best in terms of price, usage, and consistent intelligence RIGHT NOW?
Ahhh claudeai do u still need proof that qwen 3.8 27b is still not pre -trained via the Claude 😂 ?
ClaudeDevs where is the bounty money ?? 😂🫨 AnthropicAI I was just running the model locally!!!
Claude finding you jobs is cool.
But what if the whole thing ran on your phone? Qwen 3.8 + RunAnywhere. Resume in, matching jobs out, swipe and apply. Basically Tinder for jobs, running locally. No cloud. No sending your resume off-device. Built with RunAnywhere.
You have reached the end of the archive
All of qwen38