Comparing cost and token usage: Opus 5, GPT 5.6 Terra, Kimi k3, Qwen 3.8 Max.

OpenAI OpenAIDevs AnthropicAI moonshot Alibaba_Qwen

Frederic TorresAug 14

Play along with this 0-shot from Alibaba_Qwen Qwen 3.8 27B at FP16 on vllm_project strapped up to NousResearch Hermes Agent👇

Digital SpaceportAug 146

I spent time testing Qwen 3.8 27B.

First impressions: - 47 tokens/sec with MTP. - It is a real improvement over 3.6 in quality on the voxel test. All the elements are properly grounded, nothing upside down, and and nice movement in the water. - It thinks ALOT. Nearly unusable on

Jackson AtkinsAug 147

And here are Qwen 3.8 27b Q8 websites definitely better than the NVFP4.

Also getting really good game generation with Q8. Q8 is a win.

Loktar 🇺🇸Aug 1436