Qwen3.8-Max: A New Bar for Coding and Cowork

Post by colingauvin » Mon, Aug 03, 2026, 2:09 PM UTC

HarHarVeryFunny wrote: post #423

toshinoriyagi wrote: post #8

They've also announced Qwen3.8-27B being released open-weight next week. Qwen3.6-27B is widely regarded as one of the best local models, especially since nothing else comes close to it, that isn't benchmaxxed, without being significantly larger. If 3.8 truly improves upon it that would be awesome.

There was an interesting interview by MLST with a team doing well on ARC AGI 3 who are using Qwen 3.6 27B, and said that it's actually better at coding than the larger 3.6 35B. I guess which of the smaller 3.8 models is best for coding will depend on which one they put the training effort into.

Post by bruce343434 » Mon, Aug 03, 2026, 2:09 PM UTC

Iolaum wrote: post #390

jpgvm wrote: post #375

Earlier quoted context omitted.

They can be deterministic. We did this at Groq, if you sent a request with exactly the same input token, seed and temperature value you would get precisely the same result every time. This is harder to do on other architectures that themselves aren't fully deterministic though.

Was the temperature 0? Cause unless I don't understand it right, any non-zero temperature implies probabilistic next token prediction. You did mention, seed, which I haven't seen available anywhere else (in my limited experience) and it can explain a reproducible inference result, but I feel like this matches the "letter of the law" meaning of deterministic rather than the "spirit of the law".

Post by myaccountonhn » Mon, Aug 03, 2026, 2:12 PM UTC

aliljet wrote: post #79

I'm trying and failing to find value running a potential Qwen 3.8 27b dense model on a 16 core, 128 GB of ram, 2080ti box. Yes, the GPU yells for help, but the problem is that no math works to upgrade this machine even when pouring $200 in rent every month into the large model providers... How are you all justifying economical use of these local models right now? What's the cost efficient way to do this and do better…

Post by beltsazar » Mon, Aug 03, 2026, 2:15 PM UTC

Aurornis wrote: post #412

trollbridge wrote: post #149

Earlier quoted context omitted.

Qwen-3.6-35B-A3B was our "gateway drug" into switching our organisation to agent/harness-first coding. Particularly, I had one team member who was extremely sceptical of AIs/LLMs/harnesses and refused to use them. One day he said "Well, I have an RTX 5090 doing nothing... should I try to get something up on it?" and a few minutes later he had 3.6-35B loaded up, running OpenCode. It continues to be a workhorse to this…

I’ve run 3.6-27B and 3.6-35B on 32GB locally for a lot of bulk non-code tasks. Let it run overnight and wake up to millions of output tokens worth of results without data having left my house, all for the price of electricity. I haven’t found it very useful for code. It can do some code, but I’ve tried a dozen different quants and context lengths and the output is always bad enough that it has to be discarded for any…

Post by satvikpendem » Mon, Aug 03, 2026, 2:24 PM UTC

ListeningPie wrote: post #361

satvikpendem wrote: post #334

Earlier quoted context omitted.

Google figured this out with their paper from 2023, We have no moat and neither does OpenAI . The moat now is the harness and being able to recursively self improve from RLHF, a great example is how Grok used to be pretty bad but since SpaceX bought Cursor, they used that data to train Grok 4.5 which is now very competent at coding and even exceeds frontier models in certain benchmarks. https://www.semianalysis.com/p…

And yet investment is continuing. What are they counting on?