Qwen 3.8 Max vs GPT 5.6 Sol
“Whatever is frontier now…
Will become way way cheaper to run in 6 months.” Tibo is obviously right. 6 months ago Opus 4.6 was the SOTA frontier. Today you can run a 27B model (Qwen 3.8) on a gaming GPU that beats it on some of the coding benchmarks. Really great interview by
47 models at $0, no card, no subscription.
The bill arrives as tokens per second instead CDG wrote the setup honestly: one key, two minutes, any OpenAI compatible tool, and every model ending in -free costs nothing in either direction. The strongest line in it is that the same
Qwen 3.8 27B run on a single 8GB GPU locally
And somehow it outperformed Claude Opus 4.6 on multiple one-shot creative tests. - 70k context. - IQ4_XS quantization - Q4 KV cache No agents add or No looping, Just only local power. Results: you see One-shot Minecraft scenes,
You have reached the end of the archive
All of qwen38