Local Model Downloads Surge as Interconnects Updates Its Tracking Pipeline

What happened

A gap in our methodology that highlighted a decline has been fixed: we weren’t including local models (GGUF, AWQ, ONNX, etc.). Earlier, these were far harder to track and closer to a rounding error. Now, they’re surging. We updated our pipeline to track these models!

The story so far

Nathan Lambert said Interconnects updated its model-download tracking pipeline to include local models in formats such as GGUF, AWQ, and ONNX, fixing a gap in the methodology behind its earlier report of declining Hugging Face downloads. He said downloads of those previously excluded models are now surging. Lambert had reported a continuing decline among the top open LLMs Interconnects tracked, with many showing roughly a 30% drop in download rate. He initially suggested a change in download counting might explain the drop. His later explanation identified the exclusion of local models, which he said had previously been harder to track and accounted for a much smaller share of downloads.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights