Qwen Code: what 19 developers actually say.
19 Hacker News opinions from 16 developers, Nov 2025 – Nov 2026. 17 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for Qwen Code, in one paragraph.
Qwen Code earns 63% approval across 19 opinions. Developers are divided on it.
Pick it if you
- Want a generous free daily token quota
- Run models locally and want no queues or token dependence
- Care more about cost per result than top-tier model quality
Look elsewhere if you
- Need dependable file writes and tool calls
- Share a local LLM server with other users
- Need the strongest model available for hard tasks
Where it wins and loses.
Mentions across 19 opinions. Bars are counts, not votes; a tool can be both praised and criticized on the same topic.
View data table
| Topic | Praise | Complaints | Mentions |
|---|
How opinion has moved.
Monthly approval, Nov 2025 – Feb 2026. Bars show opinion volume; low-volume months are still included but faded.
Not enough monthly data for a trend yet.
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedQwen Code feels faster and nicer to work with than Claude, though less smart.
Used Qwen CLI on a hobby project; it finished 95%, slightly below top Anthropic and OpenAI models.
Qwen Code's free daily quota is very generous, around 300M tokens a day for them.
Reports good cost-benefit results using the Qwen CLI with its coder model in the cloud.
Complaints
4 selectedQwen Code immediately launched about six parallel subagents, overloading a shared local LLM server.
Qwen Code still failed on write_file tool calls when using Qwen3.6 27B.
Lost work with Qwen Code when it got confused after running out of tokens.
Codex is about twice as good as Qwen Code.
Questions developers ask.
Is Qwen Code worth it?
Is Qwen Code better than Claude Code?
Does Qwen Code have a free tier?
The data behind this page.
Qwen Code holds 63% approval across 19 opinions from 16 authors, and 17 of those opinions come from firsthand use. Cost is the clearest strength with 4 positive cost comments and no negative ones, including a report of about 300M free tokens a day. Reliability is the weak spot at 1 positive and 4 negative comments, with reports of failed write_file calls, lost work after token exhaustion, and subagents overloading a shared local server. Monthly approval fell to 0% in July and October 2026, though each of those months rests on a single opinion.
Every number comes from public Hacker News comments collected through the HN Search API. A language model tagged each comment for sentiment, first-hand use, topic and switches; a human spot-checks samples. No vendor can pay for placement.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.