Tagged with

1 article found

AMD Just Served 7K tok/s on a 27B Model: Did We All Write Off Radeon Too Soon?

A developer pushes Qwen3.8-27B FP8 to 7,025 tok/s prefill on four Radeon AI PRO R9700s. Here’s how, at what cost, and why NVIDIA’s stranglehold on AI is cracking.

#amd#fp8#qwen...