← Front page

Machine Learning Street Talk · Monday, July 13, 2026

The Challenge of Inference: Why Practicality Matters in LLM Deployment

Alistair Pullen argues that the difficulty in running large models, like Deep Seek V4 Pro with 1.6 trillion parameters, is a major reason why open-source models struggle to match the performance of commercial offerings. He highlights that the need for extensive hardware resources for inference limits adoption.

personAlistair Pullen

The tape

3 quotes
um And and my view is that the reason for these architectural decisions is largely for inference ability of the model.
Alistair Pullen
Like, sure, great that you have those top line 1.6 trillion parameters, but like if no one can run it because they need two nodes of B300s just to be able to like fit it into memory and actually, you know, run it decent TPS, then like how many people can actually take advantage of that?
Alistair Pullen
I think that is one of the reasons that whether it be like Chinese open source or European or American open source has has not reached Cloud's performance is like there is that pragmatic question of, okay, well the labs have a huge number of GPUs, um and they have enough inbound demand to make sure those GPUs are utilized to a level where then they're not that worried about having them up, whereas, you know, the open source community doesn't really have the same the same argument.
Alistair Pullen
Heard on Machine Learning Street Talk — “Why a Nation Can't Outsource Its Frontier AI - Alistair Pullen (Cosine AI), published Monday, July 13, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.06