Qwen 3.6 35B A3B: what 40 developers actually say.
40 Hacker News opinions from 34 developers, Nov 2025 – Nov 2026. 32 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for Qwen 3.6 35B A3B, in one paragraph.
Qwen 3.6 35B A3B earns 70% approval across 40 opinions. Developers are divided on it. In the last 90 days it sits at 56%.
Pick it if you
- Run agentic coding locally on a machine with under 24GB of VRAM
- Want fast local inference on Apple Silicon
- Need a private local model for rote tasks and point fixes
Look elsewhere if you
- Need reliable multi-step agents that run unattended
- Expect professional instruction following on complex design work
- Need output close to Sonnet or Opus class models
Where it wins and loses.
Mentions across 40 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 |
|---|---|---|---|
| Speed | 13 | 1 | 14 |
| Code quality | 8 | 4 | 12 |
How opinion has moved.
Monthly approval, Apr 2026 – Sep 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Apr 2026 | 81% | 8 |
| Jun 2026 | 68% | 19 |
| Jul 2026 | 83% | 3 |
| Sep 2026 | 50% | 6 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedUses Qwen 3.6 35B-A3B as the main agentic model on systems under 24GB VRAM.
Found the mxfp4 build the best balance of speed and output quality in local refactor tests.
Qwen3.6 35B-A3B runs fast in their local llama.cpp setup on a MacBook Pro.
On an M1 Max, says Qwen 3.6 35B A3B gives better responses than Gemma 4 26B A4B at similar speed.
Complaints
4 selectedQwen3.6-35B/A3B is about 4x faster but noticeably dumber and fumbles tool use.
Qwen 3.6 35B-A3B is only worth using for uncensored tasks, such as reverse engineering.
Qwen 3.6 35B-A3B could only make surgical edits, unlike the newer Qwen 3.8 27B.
Qwen 3.6 35B A3B is too weak and slow for non-trivial agentic work on their machine.
Questions developers ask.
Is Qwen 3.6 35B A3B worth it?
Is Qwen 3.6 35B A3B better than Claude Code?
Can Qwen 3.6 35B A3B run locally?
The data behind this page.
Developers give Qwen 3.6 35B A3B a 70% approval score across 40 opinions from 34 authors, and 32 of those opinions come from firsthand use. Speed is the clearest strength at 13 positive mentions to 1 negative, and local privacy use gets 6 positive mentions with no negatives. Code quality is split at 8 positive and 4 negative, while reliability and autonomy each draw more complaints than praise. Approval drops to 56% over the last 90 days on 9 opinions, down from 81% in April 2026, so recent sentiment is weaker than the overall figure.
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.