I ran 120B MoE models on my M1 Max

Details werden geladen...

I ran 120B MoE models on my M1 Max | TLDR

An engineer developed a prototype inference engine to run large mixture-of-experts language models on an Apple M1 Max with 32GB of RAM by keeping most…

synchopate/llama-modchip: Run Frontier MoE Models on Pure… | TLDR

Progress on provable inference for large language models | TLDR

GLM-5.3-Flash served on single NVIDIA B200 with FreeToken | TLDR

Qwen 3.8 27B on my laptop can interpret model weights, too | TLDR

Meta Releases Muse Spark Open, an Over 800 Billion Parameter Model That Can Run Locally on Multiple M5 Ultra Mac Studios - MacStories

“I went to the premiere of the movie and it opens with the shoes dancing and the song comes on. I turned to my wife and said, ‘This is a home run!’ It was so good”: The inside story of a classic ’80s ...

Registrieren

I ran 120B MoE models on my M1 Max | TLDR

synchopate/llama-modchip: Run Frontier MoE Models on Pure… | TLDR

Progress on provable inference for large language models | TLDR

GLM-5.3-Flash served on single NVIDIA B200 with FreeToken | TLDR

Qwen 3.8 27B on my laptop can interpret model weights, too | TLDR

Meta Releases Muse Spark Open, an Over 800 Billion Parameter Model That Can Run Locally on Multiple M5 Ultra Mac Studios - MacStories

“I went to the premiere of the movie and it opens with the shoes dancing and the song comes on. I turned to my wife and said, ‘This is a home run!’ It was so good”: The inside story of a classic ’80s ...