DeepX tapes out second-gen AI accelerator DX-M2
What happened
On November 10, 2026, Hacker News reported that Korean edge AI chip company DeepX has taped out its second-generation AI accelerator, DX-M2. The reported inference capability: models up to 100 billion parameters at under 5W, and 10 to 30 tokens per second for models of 20 billion to 100 billion parameters with roughly 3 billion to 20 billion active parameters. The disclosed progress is the tape-out; the report gives no mass-production or launch date.
Written by AI from the coverage · updated 2 days ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageDeepX claims inference up to 100B parameters at less than 5 W
韩国边缘 AI 芯片公司 DeepX 完成第二代 AI 加速器 DX-M2 流片，可在低于 5W 功耗下推理最高 1000 亿参数模型，支持 20B-100B 参数（约 3B-20B 激活参数）模型以 10-30 tokens/s 运行。
Heat over time
Heat now 3·Comparable peak 10（Nov 10 04:00）·Comparable change over 24 hours -51%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.