ExecuteAutomation

ExecuteAutomation helps people to understand software, automation, AI, cloud, testing, & more..

Available on YouTube, Medium & Udemy. Teaching over 350,000+

[ExecuteAutomation @ExecuteAuto]

@coldniko can you please add support for DeepSeek V4.1-Flash for poor Mac guys 😀

https://t.co/m917hLD6u4

I see only windows is supported in the release notes

Looking forward to tryout how fast it runs in Mac Mini and MacBook Pro M5 Max !

[ExecuteAutomation @ExecuteAuto]

@MiniMax_AI M3.1 Flash with 428B vs GPT Sol 6.1

https://t.co/AJ1LSNva7I

[ExecuteAutomation @ExecuteAuto]

@loktar00 Me too !

[ExecuteAutomation @ExecuteAuto]

@coldniko That’s great , thank you so much

[ExecuteAutomation @ExecuteAuto]

Running Strata new app (0.2.2) and latest engine (0.1.47) in Apple M6 Mac mini with Gyro S model and getting ~9TPS

@coldniko is there any optimization or new optimized models coming for these smaller machines ?

[ExecuteAutomation @ExecuteAuto]

@coldniko That will be great @coldniko , there is a Laaarge User base for this segment you are working on and it will be a huge win for Strata

[ExecuteAutomation @ExecuteAuto]

New Strata App: Qwen3.8-Flash-Next Q5 at 1M Context on M5 Max + Q2 on M6 Mac mini @coldniko

https://t.co/WXvjWcSt65

[ExecuteAutomation @ExecuteAuto]

@coldniko

[ExecuteAutomation @ExecuteAuto]

@mhelcig @coldniko @adotdad Which model is this again ?

[ExecuteAutomation @ExecuteAuto]

@coldniko Trying out now with 5bit quant and 1M context !

[ExecuteAutomation @ExecuteAuto]

@protect_whales @_yorunoken @coldniko There is a video now with 1M Context https://t.co/Nkmo1m7OKL

[ExecuteAutomation @ExecuteAuto]

1Million Token Context for QWEN3.8-Flash-Next Model in Strata of @coldniko

Getting 131 TPS in Apple M5 Max

Tell me if I am doing something wrong or Strata is good 😊

[ExecuteAutomation @ExecuteAuto]

@protect_whales @_yorunoken @coldniko Im going to do a run today and keep you all posted !

[ExecuteAutomation @ExecuteAuto]

@coldniko There is a video now with 1M Context https://t.co/Nkmo1m7OKL

[ExecuteAutomation @ExecuteAuto]

Running QWEN 3.8-FLASH-NEXT with 1Million Context with Strata in Apple M5 Max @coldniko

https://t.co/O5iKWMeDuB

#executeautomation #strata

[ExecuteAutomation @ExecuteAuto]

@liquidai LFM2.5-24B Hits 70 TPS on
@Apple
Mac mini M6, I am executing the model for OpenClaw with 128K Context!

Checkout here 👇

https://t.co/0TXTEfRh9M

#executeautomation #liquidai

[ExecuteAutomation @ExecuteAuto]

@liquidai LFM2.5-24B Hits 70 TPS on @Apple Mac mini M6, I am executing the model for OpenClaw with 128K Context!

Checkout here 👇

https://t.co/0TXTEfRh9M

#executeautomation #liquidai

[ExecuteAutomation @ExecuteAuto]

@coldniko Tried with 1M context length in my Apple M5 Max

Got 131 TPS with just 70GB of RAM used

[ExecuteAutomation @ExecuteAuto]

@trymirai Uzu on Apple M5 max and Apple M6 Mini

We are getting Faaaaast Tokens in local machine 💨

https://t.co/Abnra9gzYl

[ExecuteAutomation @ExecuteAuto]

@unbug @coldniko - see how your work is inspired here ❤️