Qwen 3.7 Max Benchmarked vs Qwen 35B - 16GB Local vs the Cloud
In this video I'd like to check out the best model I can run locally from Qwen with decent speeds, vs the best Qwen has to offer in the cloud. I am going to be looking at Qwen 3.7 Max, and seeing how it compares to Qwen 35B A3B, something a lot of us can run locally. How does the local model compare? At what point do we need the power of the cloud? Get 80% off your first month of ClinePass: https://cline.gg/luke80 I run through a few tests which are: 1. Performance 2. Memory 3. Agency 4. Driving Game 5. Kanban 6. Codebase Prompts If you're interested in local LLMs, AI and homelabs - feel free to subscribe! Qwen 3.7 Max: https://qwen.ai/blog?id=qwen3.7 Qwen 35B A3B: 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 #moe #qwen3.7 #3.7 #max This video is sponsored by ClinePass. Chapters: 0:00 Intro 0:27 Models 1:07 ClinePass 1:59 Tests Overview 2:47 Target System Specs 3:05 ClinePass Usage 3:32 Performance 4:46 Memory 6:18 Agency 7:11 Cline CLI Setup 8:36 Driving Game - Qwen 3.6 10:01 Driving Game - Qwen 3.7 12:12 Kanban - Qwen 3.6 15:49 Kanban - Qwen 3.7 18:45 Codebase Explained - Qwen 3.6 20:08 Codebase Explained - Qwen 3.7 21:26 Codebase Refactor - Qwen 3.6 32:05 Codebase Refactor - Qwen 3.7 24:06 Conclusion
ThinkingCap Qwen 3.6 27B MTP benchmarked vs Base Qwen 27B - 16GB Local LLM setup
New #1 open source AI model is here! FABLE LEVEL
LLM battle 1
DO NOT BUY: LG’s Spyware TVs, Monitors, and Wiretapping Concerns
Running a local LLM with two GPUs
The Great Bun Rewrite
Gemma4 12B Coder - Composer 2.5 × Fable 5 v2 vs base - 16GB Local LLM setup
They just failed to launch
Cohere Labs North Mini Code 1.0 Tested - 16GB Local LLM setup
Ornith 9B Benchmarked vs Qwen 9B - Local 8GB GPU LLM options
The Linux Kernel is Falling Apart.
The Local AI Hardware Mistake Everyone Makes
Can a Small Local LLM Actually Build a Useful App?
‘AI code is insane trash’ | David Gerard
LIVE: The /wayfinder Demo
Qwythos 9B MTP v3 Benchmarked vs Qwen 9B MTP - 16GB Local LLM setup
Qwable 3.6 27B tested - 16GB Local LLM setup
You Can Learn AI Agent Harness & Loop Engineering In 19 Min | LLM Ops, Eval, Tracing, RAG
VibeThinker 3B - Taking on Giant Models
