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.
More from Models
- Qwen 2.7B local deployment: Unlimited tokens and jailbreaks — lxfater · 2026-08-20
- Are models great at cybersecurity because they're 200IQ or exhaustive crackers? — chrisalbon · 2026-08-20
- GLM 5.3 lands on Merge Gateway, Artificial Analysis score up 53 to 60 — shensi · 2026-08-20
- Agent cost-efficiency plot: Qwen hits Pareto frontier — MikePFrank · 2026-08-20
- Analysis estimates GPT-5.6-Sol params at 1.5T to 2.5T — scaling01 · 2026-08-20
- ChatGPT Down: Login and Signup Issues Reported — ns123abc · 2026-08-20