I stopped using Qwen and Gemma after finding a local LLM that actually thinks before answering
… The actual issue is hardware. …
Search
I gave Qwen 3.8 27B a reverse-engineering job I assumed needed a frontier model, and it finished in 30 minutes
… My Bachelor’s thesis was conducted on the viability of benchmarking the non-functional elements of Android apps and smartphones such as performance, and I’ve been working in the tech industry in some way or another since 2017. …
I tested a local LLM against a frontier cloud model, and the gap was smaller than I expected
… Both models could research But one didn't tunnel vision The two hardware questions turned out to be mirror images. …
I ran Gemma 4 and Qwen 3.5 for the same local tasks, and one pulled miles ahead
… Latency is also faster on my hardware since the model's optimized for edge. …