Laguna S 2.1: A Compact AI Model That Outperforms Giants in Coding
We are thrilled to introduce Laguna S 2.1, a powerful 118B parameter model that punches well above its weight class. Despite its compact size, it rivals massive models on long-horizon coding benchmarks while supporting a 1M token context window. We developed this model in under nine weeks and are releasing full evaluation trajectories to ensure complete transparency in our rigorous testing process.
Laguna S 2.1 is, as far as we can measure, the most capable agentic coding model in its weight class by a wide margin.
- Lwerewolf
Testing it now. At the very least, competitive with DS4-Flash indeed. On my small (and per Sol's words, _very_ semantically dense) C test codebase, it found things that only gpt-5.2 managed to find back in the day, but also made a stupidly incorrect initial observation that a memfd_create()/mmap was used for IPC (funnily enough - sol missed that as well in its review, until I pointed it out). Re: the claims vs deepseek v4 - both flash and pro are expected to get a "general availability" release very soon (i.e. well-"post-trained"), so things can change in a... well, flash, as per usual in the current environment.
Anyways, keep 'em coming.
- river_otter
Hey, this model is not a joke! Exciting, we already got a usable PR of work out of it.
- mchusma
Incredible. This is definitely the launch of the day. Just crushing Google's releases.
The pricing here is incredible. This is the first US release that's competitive with DeepSeek V4 Flash. Very excited about this.
- mft_
Looks impressive, and this size fits achievable home hardware.
That said, if someone would kindly quantise this down for the 64GB paupers, that would be appreciated. (I know there’s likely degradation, but some people reported good results with a 2 bit version of Qwen 3.5 122B, and this is starting from a higher point. Would be interesting to try, at least.)
Edit: someone in the process of doing so: https://huggingface.co/vcruz305/Laguna-S-2.1-GGUF
- kamranjon
Whoa whoa whoa, 118b params, 8b active MOE, long context reasoning, open weights - music to my ears. Hadn't heard of this lab before but I am very excited, will definitely try this out tomorrow - this is a real sweet spot I think in terms of model size and performance.