Running a 26B Model on an Old Xeon
neomindryan · hn · 2026-07-15
This article demonstrates running Gemma 4 26B on a 13-year-old Xeon machine without a GPU, achieving a speed of about 5 tokens/s.
The focus is on viable inference on low-end hardware. The author uses this post to illustrate that running large models doesn't strictly require modern GPUs.
More from Infra
- NeurIPS 2026 workshop will focus on on-device intelligence and local execution — YiMaTweets · 2026-07-21
- How to build a PostgreSQL-backed semantic search pipeline with pgvector and Ollama — KhuyenTran16 · 2026-07-21
- NeurIPS 2026 workshop calls papers on on-device intelligence — YiMaTweets · 2026-07-21
- Milled from Solid Aluminum: AI Rig Multi-GPU Case for Local Compute — dee_hw · 2026-07-21
- FutureCaribbean’s Buildathon offers $50K, H200 compute, and an NYSE pitch — HeyAmit_ · 2026-07-21
- A new series tests which data-science workflows can run on GPUs today — pandeyparul · 2026-07-21