Top open LLM HuggingFace downloads drop ~30%, self-hosting decline suspected
iamtrask · x · 2026-10-11
natolambert reports a 30% drop in HuggingFace download rates for tracked top open LLMs; some may be a counting change, but the decline continues over time. iamtrask guesses people spend less time self-hosting models, leaning on services like Fireworks AI and Tinfoil instead. The thread hints at a cooling self-deployment trend for open models.
More from Infra
- a16z: Agents burn 5x more tokens than humans, up 14x in six months — GregCook2011 · 2026-10-11
- Codebase test: Telnyx-hosted GLM runs 9% cheaper, 5% faster than OpenAI — SucceededMind · 2026-10-11
- Nvidia said to go head-on with frontier labs as labs build their own ASICs — pzakin · 2026-10-11
- Local LLM user on RTX 5090 weighs Qwen 27B vs Flash Next for coding: is a bigger model worth it? — MasterNomie · 2026-10-11
- AirLLM runs 70B models on a 4GB GPU via layer-wise inference, scaling to 405B on 8GB — JensHonack · 2026-10-11
- How close can a 5090 + 32GB RAM rig get to Codex? Dev seeks local agent coding setup — GooseEggs712 · 2026-10-11