← Today's ranking
Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU
Llama-modchip enables 284B DeepSeek inference on 64GB RAM without GPU.
“HN: 31 pts”
Why it matters
Running very large models on CPU RAM without GPUs expands the addressable market for inference beyond specialized hardware owners. This threatens the GPU-centric business model and forces hardware makers to compete on memory bandwidth and latency.
AI score breakdown
#16 that day2.60/ 10
A composite of 2.60/10 put this story at #16 for Sunday, November 8, 2026, driven mostly by technology breakthrough (5/10) and economic impact (2/10).
Technology breakthrough · weight 30%5/10
Economic impact · weight 25%2/10
Job impact · weight 20%1/10
Regional relevance · weight 15%2/10
Policy & geopolitics · weight 10%1/10
Composite is the weighted sum of the five dimensions. How scoring works →
Companies in this story
Related stories
- Apple is racing to make Siri more agentic · 2026-11-09
- Anduril, Qualcomm launch BlueChip, a new kind of US-made laptop · 2026-10-27
- Palmer Luckey’s Anduril is getting into laptops — and claims they’ll be American-made · 2026-10-27
- Nvidia to invest $1.5B in SB Energy as part of massive Ohio AI campus deal · 2026-09-02
- Anthropic reportedly commits US$45 billion to Nscale for AI computing capacity · 2026-08-28