The domestic open source ceiling combination is fully connected! Deepseek Harness joins forces with Qwen-3.8 27B!
For ordinary people, local deployment, data security, and complete token freedom 🙂 Without further ado, let’s start moving bricks 🧱 and try to buy two RTX 5090s first
Open source Qwen 3.8 arrives
Deepseek V4 vs Qwen 3.8
An interesting side by side that tells you the strengths of both models. Qwen (vision) looks impressive at a glance but took many iterations and kept reopening to check its work. Deepseek one-shot the code blind (no vision) Looking closer: only
Okay, I am fairly confident in my hypothesis now.
The secret sauce behind Qwen 3.8 27B becomes almost immediately evident during testing. It is not the training data. In fact, I doubt any SFT was involved at all. The model was simply allowed GRPO with a more liberal reasoning
You have reached the end of the archive
All of qwen38