deepseek-v4.1POST
AWERX 团队在 ELX3 上把 V4.1 Flash 量化到 1.62 bit/权重
团队称用自研方法对 10/17 版 DeepSeek V4.1 Flash 实现 1.62 bit/权重的量化，主打本地模型极限压缩，但未给出速度或质量数据。
Garrett Kinsman
@GeKinsman11 天前收录原推发布于 2026.10.20
Garrett Kinsman @GeKinsman原推发布于 2026.10.20
Agentic engineering is all about pushing the limits of local models. Our team member @ViC305 at @AWERXAI has achieved unprecedented quantization performance of the 10/17 release of Deepseek V4.1 flash using his own methods on ELX3 at 1.62 bits per weight.
这条是引用着另一条写的：「单张 DGX Spark 上 V4.1 Flash 1.62bpw 量化：35.5 tok/s」
x.com/gekinsman/status/2112368905285177775采集于 2026.10.20 12:05