Jun 15 2026I’ve been working with local models since they came out, and finally, they’re surprisingly good now.I have a 2022 M2 Mac with 64 GB RAM and 1TB storage and I’ve usedMistral 7BGemma 3OpenAI OSS-20BQwen 3 MOE, as well as a number of other Qwen variants like Qwen 2.5 Coderacross a lot of different system setups likeraw llama.cpp with Open WebUIllama-cpp-pythonOllamallamafiles andLM StudioWhere are local models now?Early on, models were slow, hard to use, and just not that accurate for most programming tasks. The idea that local models were severely lagging behind was largely true until, for me, the release of GPT-OSS. I have no concrete scientific evidence of this – my own personal vibe metric of “is a model good enough” is, “do I have…
Running local models is good now
Advertisement