Max Omdal on Mythryl: “Impressive results from Qwen3.8-27B. Though I still don’t see a good…”

Impressive results from Qwen3.8-27B. Though I still don’t see a good hosted solution for these smaller models. We should have an inference provider with cheap costs for this if I can run it on my MacBook. artificialanalysis.ai/models/qwen3...

artificialanalysis.aiQwen3.8 27B - Intelligence, Performance & Price AnalysisAnalysis of Alibaba's Qwen3.8 27B and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

18/8/26, 7:37 am0 reposts0 likes

Post