Posted by cmitsakis 12 hours ago
The performance/intelligence is said to be about the same as the geometric mean of the total and active parameter counts. So, this model should be equivalent to a dense model with about 10.25 billion parameters.
If you have the vram to spare, a model with more total params but fewer activated ones can be a very worthwhile tradeoff. Of course that's a big if
> Sorry, how did you calculate the 10.25B?
The geometric mean of two numbers is the square root of their product. Square root of 105 (35*3) is ~10.25.
Nevermind, the other reply clears it
If you want something closer to the frontier models, Qwen3.6-Plus (not open) is doing quite well[1] (I've not tested it extensively personally):
[1] https://artificialanalysis.ai/?models=gpt-5-4%2Cgpt-oss-120b...
No. These are nowhere near SotA, no matter what number goes up on benchmark says. They are amazing for what they are (runnable on regular PCs), and you can find usecases for them (where privacy >> speed / accuracy) where they perform "good enough", but they are not magic. They have limitations, and you need to adapt your workflows to handle them.
I'm just starting my exploration of these small models for coding on my 16GB machine (yeah, puny...) and am running into issues where the solution may very well be to reduce the scope of the problem set so the smaller model can handle it.
If you perform the inference locally, there is a huge space of compromise between the inference speed and the quality of the results.
Most open weights models are available in a variety of sizes. Thus you can choose anywhere from very small models with a little more than 1B parameters to very big models with over 750B parameters.
For a given model, you can choose to evaluate it in its native number size, which is normally BF16, or in a great variety of smaller quantized number sizes, in order to fit the model in less memory or just to reduce the time for accessing the memory.
Therefore, if you choose big models without quantization, you may obtain results very close to SOTA proprietary models.
If you choose models so small and so quantized as to run in the memory of a consumer GPU, then it is normal to get results much worse than with a SOTA model that is run on datacenter hardware.
Choosing to run models that do not fit inside the GPU memory reduces the inference speed a lot, and choosing models that do not fit even inside the CPU memory reduces the inference speed even more.
Nevertheless, slow inference that produces better results may reduce the overall time for completing a project, so one should do a lot of experiments to determine an appropriate compromise.
When you use your own hardware, you do not have to worry about token cost or subscription limits, which may change the optimal strategy for using a coding assistant. Moreover, it is likely that in many cases it may be worthwhile to use multiple open-weights models for the same task, in order to choose the best solution.
For example, when comparing older open-weights models with Mythos, by using appropriate prompts all the bugs that could be found by Mythos could also be found by old models, but the difference was that Mythos found all the bugs alone, while with the free models you had to run several of them in order to find all bugs, because all models had different strengths and weaknesses.
(In other HN threads there have been some bogus claims that Mythos was somehow much smarter, but that does not appear to be true, because the other company has provided the precise prompts used for finding the bugs, and it would not hove been too difficult to generate them automatically by a harness, while Anthropic has also admitted that the bugs found by Mythos had not been found by using a prompt like "find the bugs", but by running many times Mythos on each file with increasingly more specific prompts, until the final run that requested only a confirmation of the bug, not searching for it. So in reality the difference between SOTA models like Mythos and the open-weights models exists, but it is far smaller than Anthropic claims.)
Unless there's been more information since their original post (https://red.anthropic.com/2026/mythos-preview/), this is a misleading description of the scaffold. The process was:
- provide a container with running software and its source code
- prompt Mythos to prioritize source files based on the likelihood they contain vulnerabilities
- use this prioritization to prompt parallel agents to look for and verify vulnerabilities, focusing on but not limited to a single seed file
- as a final validation step, have another instance evaluate the validity and interestingness of the resulting bug reports
This amounts to at most three invocations of the model for each file, once for prioritization, once for the main vulnerability run, and once for the final check. The prompts only became more specific as a result of information the model itself produced, not any external process injecting additional information.
Running at a full load of 1000W for every second of the year, for a model that produces 100 tps at 16 cents per kWh, is $1200 USD.
The same amount of tokens would cost at least $3,150 USD on current Claude Haiku 3.5 pricing.
It's better than 27b?
This model is the first that is provided with open weights from their newer family of models Qwen3.6.
Judging from its medium size, Qwen/Qwen3.6-35B-A3B is intended as a superior replacement of Qwen/Qwen3.5-27B.
It remains to be seen whether they will also publish in the future replacements for the bigger 122B and 397B models.
The older Qwen3.5 models can be also found in uncensored modifications. It also remains to be seen whether it will be easy to uncensor Qwen3.6, because for some recent models, like Kimi-K2.5, the methods used to remove censoring from older LLMs no longer worked.
Not at all, Qwen3.5-27B was much better than Qwen3.5-35B-A3B (dense vs MoE).
> Despite its efficiency, Qwen3.6-35B-A3B delivers outstanding agentic coding performance, surpassing its predecessor Qwen3.5-35B-A3B by a wide margin and rivaling much larger dense models such as Qwen3.5-27B.
https://x.com/alibaba_qwen/status/2044768734234243427?s=48&t...
If you look, at many benchmarks the old dense model is still ahead but in couple benchmarks the new 35B demolishes the old 27B. "rivaling" so YMMV.
benchmarks dont really help me so much
You want to wash your car. Car wash is 50m away. Should you walk or go by car?
> Walk. At 50 meters, the round trip is roughly 100 meters, taking about two minutes on foot. Driving would require starting the engine, navigating, parking, and dealing with unnecessary wear for a negligible distance. Walk to the car wash, and if the bay requires the vehicle inside, have it moved there or return on foot. Walking is faster and more efficient.
Classic response. It was really hard to one shot this with Qwen3.5 Q4_K_M.
Qwen3.6 UD-IQ4_XS also failed the first time, then I added this to the system prompt:
> Double check your logic for errors
Then I created a new dialog and asked the puzzle and it responded:
> Drive it. The car needs to be present to be washed. 50 meters is roughly a 1-minute walk or a 10-second drive. Walking leaves the car behind, making the wash impossible. Driving it the short distance is the only option that achieves the goal.
Now 3.6 gets it right every time. So not as great as a super model, but definitely an improvement.
> This sounds like a logic riddle! The answer is: You should go by car. Here is why: If you walk, you will arrive at the car wash, but your car will still be 50 meters away at home. You can't wash the car if the car isn't there! To accomplish your goal, you have to drive the car to the car wash.
It has the wrong one in thinking. It did think longer than usual:
Direct answer: Walk.
Reasoning 1: Distance (50m is negligible).
Reasoning 2: Practicality/Efficiency (engine wear/fuel).
Reasoning 3: Time (walking is likely faster or equal when considering car prep).
...
Wait, if I'm washing the car, I need to get the car to the car wash. The question asks how I should get there.
...
Wait, let's think if there's a trick. If you "go by car," you are moving the car to the destination. If you "walk," you are just moving yourself.
Conclusion: You should drive the car.