Upcoming benchmark: Local deployment comparison of Qwen3.8, Gemma4, and GPT-OSS

karminski3 · x · 2026-08-20

An upcoming comprehensive benchmark compares local deployment of Qwen3.6/3.8, Gemma4, and GPT-OSS-20B. Running on M2 Ultra and H100, it tests 3-8bit quantization and 6 reasoning levels for Qwen3.8-27B. It aims to answer questions on performance, agent capabilities, and best coding choices.

Original post →

More from Models

Models channel →