FRAMEWIREIndonesiaUpdated Aug 14Live wire
0:00 / 0:00

Codex can now run Nemotron 3.5 Lightning!!

We added local models to Codex Router this today, so it shows up in the picker right next to Sol, Grok, Kimi, DeepSeek and Minimax. I just tested it, it works, and nothing you run through it ever leaves your machine. I can't run

ZiwenAug 1222
0:00 / 0:00

In actual testing, GLM-5.3 outperformed DeepSeek V4 Pro. This generation of GLM model has very unique capabilities and is really worth using.

It feels like every model factory is beginning to find its own unique path.

塔斯海TasihiAug 141
0:00 / 0:00

DeepSeek-SSD is on GitHub

An SSD streaming engine to run DeepSeek V4 Flash on Windows

ManyGlueAug 14
0:00 / 0:00

Is DeepSeek V4 Pro overturned? Many people started to curse.

But when I read DeepSeek’s technical report today, I found out why the video memory didn’t explode when 1 million tokens were inserted into the context. This report has a total of 58 pages, and I only focused on two numbers: the amount of single-token inference calculations and the KV cache. When V4 Pro has 1 million tokens, the calculation amount of single token inference is about 27% of that of V3, KV…

左海有个洲Aug 141