Laguna XS 2.1 33B A3B tested vs Qwen 35B A3B - 16GB Local LLM setup
In this video I want to check out Laguna XS 2.1 33B A3B from Poolside, is it smarter than the current champion - 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. Kanban 7. Dungeon Crawler 8. Blender 9. Godot If you're interested in local LLMs, AI and homelabs - feel free to subscribe! Laguna XS: https://huggingface.co/poolside/Lagun... 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 #33b #a3b #moe #poolside #laguna Chapters: 0:00 Coming Up 0:19 Intro 0:29 Model 1:35 Tests Overview 2:33 Target System Specs 2:55 Performance 3:52 Memory 4:58 Agency 6:15 OpenAI HumanEval 8:03 Sand Physics - Laguna 11:29 Sand Physics - Qwen 14:35 Kanban - Laguna 19:50 Kanban - Qwen 22:32 Dungeon Crawler - Laguna 25:43 Dungeon Crawler - Qwen 27:49 Blender - Laguna 30:02 Blender - Qwen 31:32 Godot - Laguna 32:59 Godot - Qwen 34:35 Conclusion

Running a 118B Model on 12GB VRAM. Better Qwen 35B?

Trump Bombs at White House Correspondents' Dinner & Jon Stewart Offers Comedy Tips | The Daily Show

US AI Dominance Is Over: Here's Why

AMD Says 2 Ryzen AI Halos Can Run a 400B Model... I Tested It

Local LLM performance tuning

Claude Opus 5 is a freak

TypeScript in Express – TypeScript Tutorial

DeepSeek's Founder Honest AI Predictions

Cohere Labs North Mini Code 1.0 Tested - 16GB Local LLM setup

OpenAI Shocks The World With GENIE... Almost Unlimited AI Power

Ornith 35B Benchmarked vs Qwen 35B - 16GB Local LLM setup

The PROBLEM with Capitalism - Smarter Every Day 316

RESTORE YOUR PRAYER ALTAR BEFORE IT'S TOO LATE | Apostle Joshua Selman. #apostlejoshuaselman

Framework 13 Pro: The Modular Laptop is Real!

Local AI Coding is Finally Good Enough

Freenet - Services Without Servers

This Tiny Engine Runs Impossibly Big AI Models Locally! (colibrì)

HTMX 4.0 Is Here - And There's No HTMX 3 (Here's Why)

OpenAI is massively behind its ad revenue targets | Ed Zitron

