A new GPT model just dropped for Apple Silicon. The gpt-oss-20b-tq3 is a 20B parameter MoE text generator, optimized with TurboQuant and MLX for fast, local inference on your Mac.

Build your own conversational AI or text generation app right on your laptop. This model is perfect for chatbots, creative writing, and coding assistants, all running locally without cloud costs.

@HuggingModels Wonder how this stacks up against Gemma 4 26B?

@HuggingModels apple silicon users eating good again meanwhile the rest of us are still out here balancing tensor splits, hoping llama.cpp doesn’t explode, and pretending our gaming GPUs are enterprise accelerators

@HuggingModels 0 likes and Hindu name?

@HuggingModels Pretty cool release. I'm curious to see how this 20B parameter MoE model performs with MLX and TurboQuant optimizations on Apple Silicon, especially compared to other models like Llama or Mistral.

now means now. in the grey is now...now playing in theaters everywhere. starring jake gyllenhaal, henry cavill and eiza gonzalez. written & directed by guy ritchie. get your tickets...now! 🎟️