This morning I used pi + cloud GLM 5.3 Flash to help me set up DGX Sparks and install MiaAI_lab's GLM…
This morning I used pi + cloud GLM 5.3 Flash to help me set up DGX Sparks and install MiaAI_lab's GLM 5.3 Flash EXL3 kit and model. After that, because I had to go out, I only used Hermes + Telegram to test on the street. As expected, there was a bit of a gap. Now I’m back at home and trying GLM 5.3 Flash EXL3 again. It’s faster and more accurate than I expected! All Agents will be installed immediately.
Nova 500 Million parameters
Fully Local Model. No Internet Connection Required. 120+ tokens/s with Low to Extreme Reasoning on a similar level as DeepSeek 27B parameter models 1.8 years of Research. Under 4W Coming soon.....
It didn't work...Next time I'll run it with DeepSeek Pro
AI bubble alert 🚨 $openai — $1.4T / $40B rev
$ANTHROPIC — $2T / $65B rev $DEEPSEEK — $74B / $500M rev $3.47T market cap vs $105.5B revenue. 🚨 something doesn’t add up 👀
You have reached the end of the archive
All of deepseek