Qwen 3.8 27B – a deep dive; there is a whole universe in the depths.
It took time, but it was worth it. Created with Qwen 3.8 27B Q5 XYZ. It’s so good that I might turn it into a full game.
I tested two different Qwen 3.8 27B releases.
The one of the left is and the one on the right is a combo of and The left result finished in 7 minutes and 46 seconds at a rate of 246tok/s. The right result
Full end to end pipeline for Qwen 3.8 27b with Qwen TTS with < 500 ms latency
In the past weeks, Chinese AI labs have launched their new open-source models (Kimi K3, DeepSeek V4 Flash, Qwen 3.8 Max).
As these models topped charts with much lower costs, the notion that open-source models are just budget alternatives is being challenged. In this video, we
You have reached the end of the archive
All of qwen38