Agents A1 Benchmarked vs Qwen 35B - 16GB Local LLM setup
Get started with SerpApi using 250 free credits: https://serpapi.com/?utm_source=youtu... In this video I will be looking at the new model from Intern Science - Agents A1, specifically the 35B MoE model and seeing how it compares to Qwen 3.6 35B A3B. I run through a few coding tests which are: 1. Performance 2. Memory 3. Agency 4. OpenAI Human Eval 5. Sand Physics 6. Dungeon Crawler If you're interested in local LLMs, AI and homelabs - feel free to subscribe! Agents A1: https://huggingface.co/InternScience/... Qwen: https://huggingface.co/unsloth/Qwen3.... GitHub: https://github.com/lukesdevlab/youtube HumanEval: https://github.com/openai/human-eval Patreon: / lukesdevlab #localllm #localai #homelab #llamacpp #homelab #openai #qwen #35b #agents-a1 #moe This video was sponsored by SerpApi. Chapters: 0:00 Intro 0:10 Models 0:42 Tests Overview 1:18 Target System Specs 1:40 Performance 2:51 Memory 4:25 Agency Overview 4:43 Agency Results 6:11 SerpAPI 7:13 OpenAI HumanEval 8:38 Sand Physics - Agents A1 12:45 Sand Physics - Qwen 13:59 Dungeon Crawler - Agents A1 16:16 Dungeon Crawler - Qwen 17:24 Conclusion
Ornith 35B Benchmarked vs Qwen 35B - 16GB Local LLM setup
New Skills! v1.1 brings /wayfinder, /research, /implement, /to-spec, /to-tickets
I Bought an NVIDIA DGX Spark... Here's What It Actually Does (90+ Tokens/sec)
Colibrì: Running GLM-5.2 (744B) Locally in RAM With No GPU
Up to 6x Faster AI? DFlash Explained, Deployed & Benchmarked on Qwen 3.6 27B. Lamma.cpp!
Run the GLM-5.2 on Your Laptop Locally (No GPU Needed)
VibeThinker 3B - Taking on Giant Models
4 words triggered a war
MiniCPM5 - Just How Good Can a 1B Model Be?
I Ran DeepSeek's New DSpark and Doubled My Qwen3 Model’s Speed (Here’s How)
I Asked Claude Fable 5 to Improve llama.cpp.. and It Did
Cohere Labs North Mini Code 1.0 Tested - 16GB Local LLM setup
Gemma4 12B Coder - Composer 2.5 × Fable 5 v2 vs base - 16GB Local LLM setup
The Local AI Hardware Mistake Everyone Makes
He Risked Everything To Warn You: No One Is Ready For What's Coming, And The AI Companies Know It!
I was right again
Open-Source AI Tools That Feel ILLEGAL To Use
Gemma 4 26B A4B QAT vs non-QAT - 16GB Local LLM setup
KEEP AI LOCAL! Explaining Agentic AI and The Loop
