#Qwen

A study of Qwen's AI agent reveals 4 design lessons: support discoverability, reuse familiar patterns, handle personal data carefully, and protect user autonomy.

A deep dive into Qwen3.7-Max, Alibaba's new proprietary LLM. Learn how this agent-first model excels at coding, multi-tool orchestration.

You can now access Qwen 3 Max Thinking via Vercel's AI Gateway with no other provider accounts required.

You can now access Qwen 3.6 Plus from Alibaba on Vercel's AI Gateway with no markup and no other provider accounts required.

You can now access Qwen 3.7 Max on Vercel's AI Gateway with no markup and no other provider accounts required.

We benchmarked 12 local AI models across 32 real dashboard scenarios. Here are the accuracy, speed, and multilingual results.

Qwen 3.6 27B scores 77.2% on SWE-bench Verified—within 4 points of Claude Opus 4.6's 80.8%—and runs on a single RTX 4090. For solo developers doing under ~3M tokens monthly, the local model can replace the $15/MTok blended API cost.

Claude gets 3 retries. Qwen gets 6. Everything else gets 5. That is the default fix_verify_retry_cap...

From Dev.to - ai: LLaMA.cpp Gets Qwen MTP Boost, Ring-2.6-1T for Ollama, AMD GPU Fixes

Which of the new open-ish frontier models has the best chance to stand up against closed-source...

A measured developer review of Alibaba's Qwen 3.6 Plus API — pricing vs GPT and Claude, 1M-token context behavior, coding benchmarks, and the access paths that actually work.

From Dev.to - ai: KIWI-CHAN GOES OFF-GRID: How Qwen 35B Taught a Digital Kiwi to Survive the Sandbox (and My GPU)

From XDA Developers: I replaced ChatGPT with a local model on my gaming PC, and it's beating the cloud where I didn't expect

Meta's Ray-Bans are falling further behind as competing smart glasses bring the heat.

Two models. Same prompt. Same five fodder files. Same 27 published posts to check for redundancy....

Qwen 3.6 Plus lands within two points of Claude Opus 4.6 on SWE-bench Verified (78.8% vs. 80.8%) at 1/30th the input price, with a 1M-token native context

From Dev.to - productivity: Why Your AI API Keeps Breaking (And How to Fix It Before the User Notices)`

From Dev.to - opensource: KIWI-CHAN BREAKS THE CLOUD CHAINS: 47% Success Rate, Zero API Calls, and the Rise of the Local LLM Aviator

Welcome back to the lab! If you’ve been following the journey of Kiwi-chan, our autonomous...

Experiments with getting usable outputs out of local models on a standard Macbook