Qwen 3.5 Small explained..
Join GTC Sessions
1. Kimi K2.5 Session: http://nvidia.com/gtc/session-catalog/sessions/gtc26-s81695/?ncid=ref-inpa-249-prsp-en-us-1-l33
2. Coding Agent Session: http://nvidia.com/gtc/session-catalog/sessions/gtc26-s81528/?ncid=ref-inpa-249-prsp-en-us-1-l33
Sign Up for NVIDIA GTC 2026: https://nvda.ws/4qTY3VX
NVIDIA RTX 4080 SUPER - Giveaway: https://docs.google.com/forms/d/e/1FAIpQLSeb_GXw5Sk85TyU__6iD_jRMbY0Ff_EWaeFjdmogBQc2HRr6g/viewform
Qwen3.5 Small variants now released by Alibaba with their 0.8B, 2B, 4B and 9B model.
We are now approaching AI being able to run on edge devices like smartphones, laptops, consumer grade graphics cards.
How will Qwen match up again other OSS models in that size, as well as even their own previous Qwen3 models at various quantization?
What is the broad market impact for IoT, edge computing and Physical AI?
#ai #qwen #alibaba #artificialintelligence
Chapters
00:00 Intro
00:54 Density of Intelligence
02:11 Inference
02:57 Shoutout: GTC 2026
03:47 Qwen2 to Qwen3.5
04:47 Release Cycle
05:07 0.8B, IoT
06:05 AI Adoption
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
Related AI Lessons
⚡
⚡
⚡
⚡
Building an AI-Powered Git Commit & PR Assistant
Dev.to · Vinayak G Hejib
Why AWS Generative AI Skills Are Becoming Essential for Cloud Developers in 2026
Dev.to · Datta Kharad
From prototype to production: the infrastructure nobody tells you about
Dev.to AI
The Final Boss of Code Is the Future of Vibe Coding
Dev.to · Greg Urbano
Chapters (8)
Intro
0:54
Density of Intelligence
2:11
Inference
2:57
Shoutout: GTC 2026
3:47
Qwen2 to Qwen3.5
4:47
Release Cycle
5:07
0.8B, IoT
6:05
AI Adoption
🎓
Tutor Explanation
DeepCamp AI