MBZUA, mostly known for their open LLMs, released their first reasoning model built on top of Qwen2.5 32B, therefore making it not truly open. This was branded by the UAE as their first major foray into open models. Their technical report goes into more detail on the training, the data used, as well as some ablation studies - the key differentiation of the model and demo is the use of inference-time scaling methods potentially similar to GPT Pro or DeepThink.
Specs
Params32B
LicenseApache-2.0
Tags
Similarity · VAIL
VAIL Fingerprint
0037:0043:005b:0093:00e4:0196:08ed:610b
Explore other models with behavioral similarity to K2-Think.
Adoption · Hugging Face
RAM score
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Hugging Face Downloads
264
last 30d
121.8K
all time
HF Likes
367
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Related Models
