VMoore Threads deploys DeepSeek-R1-Distill-Qwen-7B distilled model on its MTT S80 and MTT S4000 graphics cards, confirms that the GPUs can run CUDA code.
Moore Threads GPUs allegedly show 'excellent' inference performance with DeepSeek models : Read more
Moore Threads GPUs allegedly show 'excellent' inference performance with DeepSeek models : Read more