LLM EXPLORER 57,918 MODELS INDEXED

K2 Think by LLM360

By LLM360 · 125 downloads
HF Repo ↗ Copy URL

K2 Think is an open-source language model by LLM360. Features: 32b LLM, VRAM: 65.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.23.

  Arxiv:2509.07604 Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2.5-32b   Conversational   Deploy:azure   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LLM360/K2-Think 

K2 Think Parameters and Internals

LLM NameK2 Think
Repository 🤗https://huggingface.co/LLM360/K2-Think 
Base Model(s)  Qwen/Qwen2.5-32B   Qwen/Qwen2.5-32B
Model Size32b
Required VRAM65.8 GB
Updated2026-06-08
MaintainerLLM360
Model Typeqwen2
Model Files  4.9 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   2.1 GB: 14-of-14
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to K2 Think

Best Alternatives
Context / RAM
Downloads
Likes
Openbuddy Qwq 32B V24.2 200K195K / 65.8 GB93
Openbuddy Qwq 32B V24.1 200K195K / 65.8 GB103
Openbuddy Qwq 32B V25.2q 200K195K / 65.8 GB14
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB92
DeepSeek R1 Distill Qwen 32B128K / 65.7 GB8416331584
Qwen2.5 32B128K / 65.5 GB49206180
RomboUltima 32B128K / 20.7 GB126
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB1417
Ultiima 32B128K / 65.8 GB117
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB124
Note: green Score (e.g. "73.2") means that the model is better than LLM360/K2-Think.