20:09
2026-10-15
kernwerk.org
large-language-models
Same LLM, same input tokens, different answers on a MacBook and a Jetson
Running the same Qwen2.5-1.5B-Instruct weights on an Apple M1 MacBook in fp16 and an NVIDIA Jetson Orin Nano Super in fp16 produced scores within half a percentage point, but the generated answers dif…