[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![reach_vb Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::874987512850128897.png) Vaibhav (VB) Srivastav [@reach_vb](/creator/twitter/reach_vb) on x 32.3K followers
Created: 2025-07-21 16:21:33 UTC

missed this, @NVIDIAAIDev  silently dropped Open Reasoning Nemotron models (1.5-32B), SoTA on LiveCodeBench, CC-BY XXX licensed 🔥

> 32B competing with Qwen3 235B and DeepSeek R1
> Available across 1.5B, 7B, 14B and 32B size
> Supports upto 64K output tokens
> Utilises GenSelect (combines multiple parallel generations)
> Built on top of Qwen XXX series
> Allows commercial usage

Works out of the box in transformers, vllm, mlx, llama.cpp and more!

![](https://pbs.twimg.com/media/GwZPJHgWUAYJNQM.jpg)

XXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947331118983696907/c:line.svg)

**Related Topics**
[r1](/topic/r1)

[Post Link](https://x.com/reach_vb/status/1947331118983696907)