I didn't give our agent any images as reference but using GLM-5.3 and Qwen 3.8 27B for its eyes it did…

I didn't give our agent any images as reference but using GLM-5.3 and Qwen 3.8 27B for its eyes it did a great job and this cost a fraction of the price it cost for petergostev to have GPT-6-Astra make it.

UnivenceSep 151

DeepSeek v4.1 flash, Qwen 3.8 flash, or GLM 5.3 flash 🤯

Fabiano FirmoSep 155

You can just hallucinate the entire internet with Qwen 3.8 27b running at 2,000 tokens/second?

Part 2 of turning cerebras + Alibaba_Qwen 3.8 27B into an OS: built an offline browser with zero network calls and mounted it directly the JIT ubuntu desktop. no wifi. no scraping.

AlokSep 15229

Qwen 3.8 Max Full COURSE 1 HOUR (Build & Automate Anything)

Julian Goldie SEOSep 154