# Qwen 474 Hacker News commenters recommended Qwen and 175 criticized it, November 2025 to November 2026. It was recommended in 13 of 13 months; owners who said how long report a median of 0.5 years (6 owners). It meets the Hacker Approved badge rule. **Verdict:** The go-to open-weight model family for running capable coding and general AI locally on accessible hardware, though it falls short of frontier models like Claude Opus. ## Why people recommend it - Runs well on local hardware (8 comments): "My 64GB DDR4 laptop can already run Qwen 47B at .7 tok/s, that's already usable for some usecases (overnight stuff mostly)." ([source](https://news.ycombinator.com/item?id=48234339)) "I am feeling pretty liberated with my local Qwen, it can make copies of software, reverse engineer hardware bootloaders" ([source](https://news.ycombinator.com/item?id=50029165)) "Alibaba's Qwen is definitely competitive, and its the main story these days if you want to run a coding model locally." ([source](https://news.ycombinator.com/item?id=46664611)) - Close enough to frontier models (6 comments): "several Chinese models (at least Qwen, DeepSeek, Kimi and GLM) are "close enough" that with the right harness they are cost effective alternatives" ([source](https://news.ycombinator.com/item?id=48390313)) "It is much better than I thought it would be. But also still falls short in some obvious ways compared to the frontiers." ([source](https://news.ycombinator.com/item?id=47571474)) "Alibaba's Qwen is definitely competitive, and its the main story these days if you want to run a coding model locally." ([source](https://news.ycombinator.com/item?id=46664611)) - Open weights, cheap alternative (6 comments): "Look at qwen, gemma, etc, they can all do structured output, and they can do it locally and cheaper and/or faster than Jev!" ([source](https://news.ycombinator.com/item?id=50111904)) "DeepSeek, Alibaba/Qwen, Baidu/ERNIE, and Tencent/Hunyuan are breaking that model by releasing various open weight models" ([source](https://news.ycombinator.com/item?id=48257560)) "publish it to the public, some of not majority contribute with open-weight models making a future of local llm possible" ([source](https://news.ycombinator.com/item?id=46782040)) - Good for coding and long contexts (5 comments): "By properly structuring my project, I can point it at any extension I want and get it going for 30 minutes to extend whatever." ([source](https://news.ycombinator.com/item?id=48466408)) "Alibaba's Qwen is definitely competitive, and its the main story these days if you want to run a coding model locally." ([source](https://news.ycombinator.com/item?id=46664611)) "For anything longer form though, particularly with larger code contexts, Qwen is far more useful for me personally." ([source](https://news.ycombinator.com/item?id=47984658)) ## What people warn about - Falls short of frontier models (4 comments): "The Qwen models are cool, but if you're coming from Opus you will be somewhere between mildly to very disappointed depending on the complexity of your work." ([source](https://news.ycombinator.com/item?id=47858701)) "It is much better than I thought it would be. But also still falls short in some obvious ways compared to the frontiers." ([source](https://news.ycombinator.com/item?id=47571474)) "it feels a bit like last year's Sonnet. They don't quite make the leaps of understanding you get from Opus." ([source](https://news.ycombinator.com/item?id=47638130)) - Censored on Chinese sensitive topics (4 comments): "Qwen is also censored - although since it's open weight, there are completely uncensored versions available." ([source](https://news.ycombinator.com/item?id=48740055)) "We already have censorship and state values in Chinese models (and have for awhile, ask Qwen about “sensitive” issues like Taiwan)" ([source](https://news.ycombinator.com/item?id=48075089)) "the Qwen model series considers it highly unethical to ever talk about Taiwan as anything other than a renegade province of China" ([source](https://news.ycombinator.com/item?id=48070214)) - Benchmarks overstate real performance (2 comments): "they do a lot of benchmaxxing after using them. Even at full precision they're never as good as models with similar benchmarks." ([source](https://news.ycombinator.com/item?id=49301927)) "Qwen and GLM both promise the stars in the sky every single release and the results are always firmly in the "whatever" range" ([source](https://news.ycombinator.com/item?id=46977666)) - Slow or inconsistent results (4 comments): "Things that were Qwen or Gemma Diffusion did better at those kinds of tasks but were generally pretty inconsistent" ([source](https://news.ycombinator.com/item?id=49787750)) "My 64GB DDR4 laptop can already run Qwen 47B at .7 tok/s, that's already usable for some usecases (overnight stuff mostly)." ([source](https://news.ycombinator.com/item?id=48234339)) "on my setup I found it a bit slow for my use case, and the benefits weren't strong enough to outweigh the slowdown" ([source](https://news.ycombinator.com/item?id=49911998)) ## Alternatives hackers recommend - [Qwen 3.8 27B](https://hackerapproved.com/p/qwen-3-8-27b.md): 1173 recommend - [Z.ai GLM](https://hackerapproved.com/p/glm-5-2.md): 1043 recommend - [Kimi](https://hackerapproved.com/p/kimi-k3.md): 931 recommend - [Gemma 4](https://hackerapproved.com/p/gemma-4.md): 713 recommend - [Qwen3.6-35B-A3B](https://hackerapproved.com/p/qwen3-6-35b-a3b.md): 373 recommend ## Cite as Hacker Approved, "Qwen", https://hackerapproved.com/p/qwen/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).