@Daniel_Farinax: Qwen3.6-27B on MacBook Pro M5 128GB. Third version of the game. This time a low-poly GTA, built overnight using a custo…
Summary
Daniel Farinax demonstrates running Qwen3.6-27B on a MacBook Pro M5 128GB, using a custom Rust CLI (MPTLX) to build a low-poly GTA game overnight, claiming blazing fast performance comparable to Claude 4.6 running locally.
Similar Articles
@Daniel_Farinax: Qwen3.6-27B on MacBook Pro M5 128GB MLX with custom coding CLI optimized for it. Should also work on M1, M2, M3, M4 Mac…
Daniel Farinax announces a custom CLI for running Qwen3.6-27B on MacBooks via MLX, seeking beta testers and moving to TypeScript for faster iteration.
@sudoingX: update: qwen 3.6 27b dense q4 just one shotted octopus invaders game on a single 3090. hermes agent drove the whole thi…
A user benchmark demonstrates that the Qwen 3.6 27B dense model (Q4 quantized) can autonomously generate a fully playable multi-file game in a single prompt on a single RTX 3090, significantly outperforming its predecessor with zero manual interventions. The results highlight major improvements in local code generation and agentic capabilities for consumer-grade hardware.
@rohanpaul_ai: Qwen 3.6 27B on a MacBook Pro M5 Max 64GB hitting 34tokens per sec, locally with atomic[.]chat 90% acceptance rate, i.e…
Qwen 3.6 27B achieves 34 tokens/sec on a MacBook Pro M5 Max 64GB locally with 90% draft acceptance, enabled by TurboQuant, GGUF, and llama.cpp, showcasing a major advancement in laptop-based AI inference.
@0xSero: Qwen3.6-28B-REAP - BF16 (56GB) / 4bit (14GB) builds a subway shooter game (vllm-studio) 150 tok/s per session. Relative…
Qwen3.6-28B-REAP, a new 28B parameter model variant, is released with BF16 (56GB) and 4-bit (14GB) versions, capable of building a subway shooter game using vllm-studio at 150 tok/s per session.
@ngxson: Qwen3.6-27B running 100% on WebGPU. Not the best speed but still
A developer demonstrates running the Qwen3.6-27B AI model entirely on WebGPU in a browser, though speed is not optimal.