[Topic] An individual trains a 4B model that is ``81% faster than Postgres'' for $1,200
One person on sabbatical trained Qwen 3.8 4B in RL and optimized Postgres execution plans. Geometric mean 1.81 times and delay reduced by 44.7% for 113 queries. HN 562pt, a hot topic overseas (based on personal reports) Video: From his blog
Closest i can get so far using qwen 3.8 max, thoughts?
Which local AI should drive your browser?
🧠 I gave Gemma 4 and Qwen 3.8 four jobs in four browser tabs at once, all on my Mac, no cloud Both got every answer right. Gemma was over 2x faster Want a browser agent that multitasks? Start with Gemma 4
Introducing MTPLX V2.11.3
The fastest way to run AI models on your mac now perfectly exact. Qwen 3.8 Flash Next M5 Max Macbook In OpenCode: - Peak Speed: 126.5 TPS. - Average Speed at 100k context: 61 TPS. - Average Speed at 200k context: 50 TPS. I kept hearing on
You have reached the end of the archive
All of qwen38