alt Hacker NewsThey'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.
Replies
Qwen3.8-Max is the first in Qwen-Max series to be open-weight as well.
Kimi K3, GLM 5.2 and now Qwen3.8-Max - open weight models.
DeepSeek V4 Flash outperforming Gemini 3.1 pro, probably DeepSeek V4 Pro update is also coming soon
Chinese labs are cooking very hard. US closed weight labs are probably hard time to resist not calling Washington DC for more AI regulations
Some advice I got from another HN Mac user was to run local models in energy saver mode. You'll get slightly reduced tokens, but the laptop won't overheat and the fans won't go wild.
This is what I've been waiting for. We are still using fine-tuned deployments of Qwen3.6-27B with a lot of success but could use a bump in intelligence. Here's hoping.
Really awesome. Though I wish they'd do a dense 48B, 60B or 72B.
There seems to be quite a gap between the small ones and the enormous ones these days.
Qwen 3.6 27b has been the sweet spot for me in terms of local models. I've had good luck using it with Pi harness. Looking forward to this.
Having invested in a machine with 128GB of RAM, I would love seeing something a bit larger than 27B / 35B, possibly a 54B dense model or 70B MoE would be much closer to the Qwen 3.8 Max experience.
The 27B have many more active parameters than much bigger models such as DS4Flash, MiniMax etc, which makes it punch above its tiny weight. A great fit for a 5090 in a closet for meat-and-potatoes, kind of work.
I've been running Qwen3.6-27B-IQ4 (4-bit quantized) locally and it's been great. I can't run the non-quantized version as I only have a 4090 w/24 GB of VRAM and it won't fit and leave any context room, but the quantized version only uses 18GB.
Yeah, Qwen3.8-Max is the new Flagship model for coding and harness system and many other benchmarks are reaching equal performance as Claude and other close models. That's gonna drop the price of LLM in agent landscape a lot.
the bonsai 27B 1bit quant version of Qwen3.6 27B is even more nuts, model fits in 4GB, and with 100k of content model+kv cache fits in 8GB. I’ve been running it locally on my mac mini 16GB. it gets around 4-6 tok/s, so not quite real-time ready, but good enough to let it run on task async for 20 min and come back. The 1bit model struggles a bit with multi-turn conversations though (e.g. when switching from plan to act mode it will still keep trying to make a plan) but that’s easy enough to reformat prompts into multiple one shot sessions of smaller work.
You consider that even Gemma 4 31B is not even competing with Qwen 3.6 27B?
For those of us who don't have the time to follow closely, Qwen3.6-27B being Open Source and Open Weight, what level is this compared to other Western paid version?
Just so that we know what 3.8 would be like.
I currently have about 150 Tabs of Antirez posting on AI and running local model I haven't had the time to read. And there are probably some prerequisite reading or other research in between as well. I just wish there are some very high level overview and news coverage on all these.
If they trained it well, and can do computer use, it will be a new era. Companies can keep PCs, put Qwen 3.8 27b on it and get rid of the employees, lol...
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.
as much as im excited for it, sadly it gonna be one of the reasons to push ram prices higher
Qwen3.6-35B is my daily driver for AI, and what convinced me to cancel my Claude subscription back in April. The Qwen3.6 line is easily the best local model I've tried, and I've tried a lot. I've got it diligently grinding away on my laptop right now, reviewing and fixing some bugs in my F# code.