@ExecuteAuto
Account based inNew Zealand!
About this account
- Account based in
- New Zealand
- Connected via
- New Zealand App Store
X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
ExecuteAutomation helps people to understand software, automation, AI, cloud, testing, & more.. Available on YouTube, Medium & Udemy. Teaching over 350,000+
Auckland, New Zealand
Joined March 2015
- Tweets2.2K
- Following170
- Followers883
- Likes258
New Strata App: Qwen3.8-Flash-Next Q5 at 1M Context on M5 Max + Q2 on M6 Mac mini @coldniko
youtu.be/DWqHGeNExgA
Running QWEN 3.8-FLASH-NEXT with 1Million Context with Strata in Apple M5 Max @coldniko
youtu.be/TMFCDb6mGBY?si=1ZLC…
#executeautomation #strata
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 retweeted
🚀 Unsloth v0.1.907-beta: Up to 5× faster LLM inference!⚡95% cache hit rate⚡ Strata-inspired MoE optimizations。More speed for local LLMs. 🔥
Release: github.com/unslothai/unsloth…
ExecuteAutomation retweeted
Didn’t even know I got it this good in first try on Mac… Nice video @ExecuteAuto
youtu.be/wv90cfWfhPk?is=pkpH…
Tested Mac Mini M6 with QWEN3.8-27B and I’m getting around 53tps with Splash engine
youtu.be/7ugFOo8e8H4?si=GUwl…
🤖 Made with AI
What a great time to have an Claude Opus level of Intelligent AI model running locally and doing testing for us with @Test_Sprite You can see how the Local @Alibaba_Qwen AI model runs test faster, with less token than a Cloud Model youtu.be/eKLZXVb3hs0
#qwen #testsprite
What a great time to have an Claude Opus level of Intelligent AI model running locally and doing testing for us with @Test_Sprite
You can see how the Local @Alibaba_Qwen AI model runs test faster, with less token than a Cloud Model
youtu.be/eKLZXVb3hs0
#qwen #testsprite
Happy to announce our course in Udemy on Using LangChain to build Agentic AI, RAG and ChatBots is now fully upgraded with LangGraph support
udemy.com/course/build-ai-ag…
#executeautomation #langchain #langsmith #langgraph #aiagent #chatbot #agents
Running GLM5.3 Flash in MacBook Pro M5 Max 128GB machine
youtu.be/HrUtnr5Oeto?si=ofVC…
#glm #zai #macbook
Get ~65 TPS in Apple M5 Max 128GB for QWEN3.8-Flash-Next Quant-4
More videos in @ExecuteAuto channel youtu.be/RTydhfQNBak
#executeautomation #qwen #omlx
Just tried out @Alibaba_Qwen 3.8 Flash Next and its 120TPS in Apple M5 Max machine !
youtu.be/RTydhfQNBak
#executeautomation #qwen3flashnext
I was testing Qwen3.8-27B with Experimental Apple ANE Prefill — Is it Faster or thinking?
youtu.be/b3k92MmbZ5g
#executeautomation #qwen #ane
I am Testing out @browserstack's new Test Companion, an agentic AI that generates test cases E2E
You can try BrowserStack AI Test Companion For FREE from here shorturl.at/O3Oje
Video: youtu.be/1P_E-IjUIMs
#BrowserStackTestCompanion #executeautomation #playwright
I am Testing out @browserstack's new Test Companion, an agentic AI that generates test cases E2E
You can try BrowserStack AI Test Companion For FREE from here shorturl.at/O3Oje
Video: youtu.be/1P_E-IjUIMs
#BrowserStackTestCompanion #executeautomation #playwright
Is Qwen3.8-27B Still #1 for Local LLMs? (M5 Max Test)
youtu.be/-TKu-PdHI_Y
#executeautomation #qwen #firsthandexperence #ai #localllms #llm
KAT-Coder-V2.5-Dev vs Qwen3.6-35B: Is 8x Fewer Tokens Actually Better for Agentic Coding?
youtu.be/ox6upguli7U
#AgenticCoding #LocalLLM #KATCoder #Qwen #AppleSilicon #AITesting #ExecuteAutomation
MiniMax H3 First Look — Beats Google Veo & Sora for a FRACTION of the Cost
ExecuteAutomation YT video: youtu.be/fA1Iv30vMJM
#MiniMaxH3 #AIVideo #GoogleVeo #Sora2 #OmniModalAI #executeautomation
I Ran Laguna XS 2.1 Against Qwen3.6 on Apple Silicon .. Which one does better coding ??
ExecuteAutomation YT video: youtu.be/eRjrABGMAbY
#executeautomation #qwen #laguna
