# Qwen3.6-35B-A3B 373 Hacker News commenters recommended Qwen3.6-35B-A3B and 108 criticized it, November 2025 to November 2026. It was recommended in 10 of 13 months; owners who said how long report a median of 0.08 years (6 owners). It meets the Hacker Approved badge rule. **Verdict:** A fast mixture-of-experts open model that runs well on consumer hardware and is surprisingly capable for its size, though it falls well short of frontier models on complex tasks. ## Why people recommend it - Runs fast on local hardware (9 comments): "If you have fast CPU RAM (ddr5) and PCIe bus you can run Qwen3.6-35b-a3b at good speeds+~100k context (I have a friend who is running this setup)." ([source](https://news.ycombinator.com/item?id=49956261)) "that a3b means only 3B active parameter, so while infering the entire 3B will be in your GPU and you will get amazing performance" ([source](https://news.ycombinator.com/item?id=47192670)) "35B-A3B underperforms against 27B on anything even remotely complex. But yes, 35B-A3B can be like 3-4x faster on my hardware." ([source](https://news.ycombinator.com/item?id=48213694)) - Impressive capability for its size (6 comments): "Compared to the frontier coding models like Opus 4.7 and GPT 5.4, Qwen3.6 35B A3B is not going to feel smart at all, but for something that can run quickly at home... it is impressive how far this stuff has come." ([source](https://news.ycombinator.com/item?id=47794824)) "Those Qwen 3.6 models are impressive for the size, but you need an order of magnitude more parameters to actually be useful" ([source](https://news.ycombinator.com/item?id=48885661)) "Once you can see what something like Qwen3.6-35B-A3B can do... with just a FRACTION of the size of the larger models" ([source](https://news.ycombinator.com/item?id=47852409)) - Big jump over previous models (5 comments): "The capabilities of Qwen3.6 27B or 35B-A3B are dramatically better than what was available even a few months ago." ([source](https://news.ycombinator.com/item?id=47893790)) "Qwen3.6 is a huge jump in capability. It can make improvements to a project that qwen3.5 always struggled with." ([source](https://news.ycombinator.com/item?id=47800925)) "It's surprisingly performant, even though the previous generation wasn't even able to use the testing harness." ([source](https://news.ycombinator.com/item?id=47841363)) - Handles everyday agent and coding tasks (6 comments): "Qwen3.6 35b running quantized on 10 year old hardware solves basically all of my uses cases for agents except for coding." ([source](https://news.ycombinator.com/item?id=48682413)) "anything you can reasonably expect an LLM to oneshot Qwen 3.6 35b MoE will handle at like 90tok/sec, absolutely fantastic" ([source](https://news.ycombinator.com/item?id=48090778)) "Both of them are good developer partners for an engineer who wants more of a second pair of eyes and a rubber duck" ([source](https://news.ycombinator.com/item?id=48729345)) ## What people warn about - Far behind frontier models (6 comments): "Compared to the frontier coding models like Opus 4.7 and GPT 5.4, Qwen3.6 35B A3B is not going to feel smart at all, but for something that can run quickly at home... it is impressive how far this stuff has come." ([source](https://news.ycombinator.com/item?id=47794824)) "These models are still very capable with good hardware, but they do lack the deep reasoning of major models" ([source](https://news.ycombinator.com/item?id=48553253)) "The Qwen models are decent, but they don't come close to the full Claude experience I've come to expect." ([source](https://news.ycombinator.com/item?id=49391156)) - Weak on complex coding tasks (3 comments): "35B-A3B underperforms against 27B on anything even remotely complex. But yes, 35B-A3B can be like 3-4x faster on my hardware." ([source](https://news.ycombinator.com/item?id=48213694)) "Qwen3.6 35b running quantized on 10 year old hardware solves basically all of my uses cases for agents except for coding." ([source](https://news.ycombinator.com/item?id=48682413)) "The thing that bugged me the most was really the quality of the output on moderately complex real-world coding tasks." ([source](https://news.ycombinator.com/item?id=48545399)) - Gets stuck in thinking loops (3 comments): "I had issues with Qwen thinking endlessly when I didn't know I wasn't using the temp/top_k/min_p/etc settings specified in the readme." ([source](https://news.ycombinator.com/item?id=47807850)) "I really like the 3.6 35B A3B for experiments, and it seems OK, but as you say, it spins round in thinking loops" ([source](https://news.ycombinator.com/item?id=49245383)) "I've seen reports of qwen3.5-35b-a3b spending a ton of time reasoning if the context window is nearly empty" ([source](https://news.ycombinator.com/item?id=47203517)) - Mistakes and hallucinations (2 comments): "even the 4-bit quant was more flaky (hallucinations, and sometimes it would think about running tools calls and just not run them, lol)" ([source](https://news.ycombinator.com/item?id=47492996)) "You have MoE models (gemma 26b, qwen 35b, north mini code 30b) who are pretty fast, but make a lot of mistakes" ([source](https://news.ycombinator.com/item?id=48557467)) ## 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 - [Qwen](https://hackerapproved.com/p/qwen.md): 474 recommend ## Cite as Hacker Approved, "Qwen3.6-35B-A3B", https://hackerapproved.com/p/qwen3-6-35b-a3b/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).