Swiftlet, a 10,000-line Swift and Metal project under Apache 2.0, runs Alibaba's Qwen3-Next-80B-A3B at 4-bit in 4.3GB of peak RAM on a Mac, decoding at 4.5–5 tokens per second on an M5, and runs the Q…
TurboFieldfare, an independent Swift and Metal runtime, reports running Google's Gemma 4 26B A4B Mixture-of-Experts model with a resident memory footprint of roughly 1.9–2.1GB on Apple Silicon by stre…
TurboFieldfare, a Swift-and-Metal runtime, runs Google's Gemma 4 26B-A4B model on Apple Silicon Macs with as little as 2 GB of RAM by streaming expert weights from SSD, achieving 5.1–6.3 tokens per se…
A developer has released TurboFieldfare, an open-source Swift and Metal engine that runs Google's Gemma 4 26B-A4B instruction-tuned model in about 2 GB of RAM on any Apple Silicon Mac, including 8 GB …