Really enjoying seeing these really capable SMLs.
Note that on HF they state:
"This model was not trained on tool-calling or agent-based programming data. We therefore do not recommend using it for tasks that involve function calling, API orchestration, or autonomous coding agents." - https://huggingface.co/WeiboAI/VibeThinker-3B
So we can't just hook it up to a coding harness like pi.dev or something.
VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
201–210 of 226 posts
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#202Earlier quoted context omitted.
In some countries they even let kids as young as 16 drive, no wonder they have so many accidents.
Several US states will give you a permit to drive a farm vehicle on public roads at 14. Illinois recently passed an amendment to allow farm kids to drive a semi-truck at 16. And there is absolutely no minimum age for driving so long as you are on private land - I have seen 8 year olds driving a pickup truck round a farm...
The mere fact that children as young as 16 can drive on public roads in the US is kind of crazy. On private land no one should give an ass about it, but children in traffic? Crazytalk.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#203Earlier quoted context omitted.
At least according to gertlabs, Qwen3.6 27B outperforms every SoTA (closed) model at Kotlin: https://archive.vn/RYBCL / https://gertlabs.com/rankings?mode=agentic_coding&language=k...
Interesting. I wonder if there is opportunity to train a set of small model variants to excel at a certain stacks. Eg Qwen3.6-27B for Node + React or Qwen3.6-27B for Rust + TUI
This is always how I've imagined small/consumer-hardware models going in time. If I only ever code in Python, give me a model that does just that (plus some general CS, algorithms, structure, etc.) and does it super-fast and well. Make it small enough that if I need a Python back end and an HTML front end, another specific model can load alongside and collaborate on the front end.
Or give me a pure shopping model that has a general understanding of products and product categories, and then will playwright/scrape/API into shopping sites to compare options and find me what I want. Etc.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#204Earlier quoted context omitted.
I've just started using qwen3.6:35b a couple days ago running on my framework desktop and rather impressed. It runs really well and reminds me of probably the first Claude model I used. It's the first local model that's actually working for me in a coding agent I've tried. Very exciting!
Try 27b, it's significantly smarter than 35b-a3b (although it is slower, it's not so bad with MTP).
It is, but it's way too slow on a Strix Halo due to its limited bandwidth.
(I'm still sad that they didn't make a 122B-A10B version of it, as it's the kind of model that fits best on a Strix Halo, and for 3.5 it was comparable in performance to the dense 27B version).
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#205Sounds like something that could be pretty useful as a 'validation' subagent. Provide it the details/context related to a larger LLM's run or turn in a harness and have it act as a gatekeeper. At this size and speed it looks like it could be economical to have it run every turn or even every tool call and inform the main agent about the result and success/failure.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#206Earlier quoted context omitted.
Try 27b, it's significantly smarter than 35b-a3b (although it is slower, it's not so bad with MTP).
It is, but it's way too slow on a Strix Halo due to its limited bandwidth. (I'm still sad that they didn't make a 122B-A10B version of it, as it's the kind of model that fits best on a Strix Halo, and for 3.5 it was comparable in performance to the dense 27B version).
Yeah the speed is vastly different but it's getting ~10 tps. And the MoE model is like 50 or something.
Might use it if it proves to be much smarter I dont really monitor my agents while they're running.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#207I tried actually talking to it. It reminded me of GPT-2.
It's not supposed to be a chat model. It is crazy good at math.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#208Earlier quoted context omitted.
If your framework desktop is the 128G Strix Halo, I recommend giving Qwen 3.5 122B-A10B a shot. This Q5_K_M quant should be near lossless and fit with full 256K context in about 100GB of RAM: https://huggingface.co/AesSedai/Qwen3.5-122B-A10B-GGUF
3.6 scores better on coding across the board. Edit: specifically Qwen 3.6 27B beats that on coding and agentic workflows.
Vibe thinker also beats Opus 4.5