llama-modchip claims a 284B model runs on CPU with 64GB of RAM
What happened
The llama-modchip repository claims model compression and CPU kernel optimizations let a 284B DeepSeek-V4-Flash model run with 256K context on 64GB of RAM and no GPU. The report comes from the repository's claims. It gives no test results, no throughput figures and no independent verification.
Written by AI from the coverage · updated yesterday
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageLlama-modchip: 284B DeepSeek on 64GB RAM, no GPU
llama-modchip 仓库宣称，通过模型压缩和 CPU 内核优化，可在 64 GB RAM、无 GPU 环境运行 284B DeepSeek-V4-Flash，支持 256K 上下文。
Heat over time
Heat now 5·Comparable peak 10（Nov 8 20:00）·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.