Protein embedding still needs 1TB of memory and 384 CPU nodes for a single run
ebetica · x · 2026-07-22
A complaint about a protein-embedding workflow that still needs enormous resources: 1 TB of memory and 384 CPU nodes just to embed a single protein in about 10 minutes.
The point is less about one specific model than the operational absurdity of the current setup: even a single inference job can require a very large cluster footprint, which is a useful signal about the compute cost of large-scale bio/ML pipelines.
More from Infra
- Meta approves nonvoting Class C shares as 2026 capex guidance hits $135B–$145B — thione · 2026-10-26
- Unsloth Ships MiniMax-M3.1-Flash Quants: 2-bit Retains 91.5% Accuracy, Runs in 150GB RAM — danielhanchen · 2026-10-26
- Engineer with thousands of fabricated devices pours cold water on photonic crystal modulator yields — jwt0625 · 2026-10-26
- Anthropic S-1 reveals 48 cents of compute cost per dollar of Q2 revenue — nmasc_ · 2026-10-26
- Persistent AI joins UR network to route private AI inference with encrypted, IP-hidden traffic — 0xSammy · 2026-10-26
- Anthropic's disclosed compute commitments: $114.5B Google, $161.2B Broadcom top the list — BenBajarin · 2026-10-26