LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Kevin 32B by cognition-ai

 »  All LLMs  »  cognition-ai  »  Kevin 32B   URL Share it on

  91   

Kevin 32B is an open-source language model by cognition-ai. Features: 32b LLM, VRAM: 131.5GB, Context: 40K, LLM Explorer Score: 0.22.

Base model:finetune:qwen/qwq-3...   Base model:qwen/qwq-32b   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognition-ai/Kevin-32B 

Kevin 32B Benchmarks

LLME Score: 0.21738
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kevin 32B (cognition-ai/Kevin-32B)
🌟 Advertise your project 🚀

Kevin 32B Parameters and Internals

LLM NameKevin 32B
Repository 🤗https://huggingface.co/cognition-ai/Kevin-32B 
Base Model(s)  QwQ 32B   Qwen/QwQ-32B
Model Size32b
Required VRAM131.5 GB
Updated2026-04-03
Maintainercognition-ai
Model Typeqwen2
Model Files  4.5 GB: 1-of-29   4.7 GB: 2-of-29   4.5 GB: 3-of-29   4.5 GB: 4-of-29   4.7 GB: 5-of-29   4.5 GB: 6-of-29   4.5 GB: 7-of-29   4.7 GB: 8-of-29   4.5 GB: 9-of-29   4.5 GB: 10-of-29   4.7 GB: 11-of-29   4.5 GB: 12-of-29   4.5 GB: 13-of-29   4.7 GB: 14-of-29   4.5 GB: 15-of-29   4.5 GB: 16-of-29   4.7 GB: 17-of-29   4.5 GB: 18-of-29   4.5 GB: 19-of-29   4.7 GB: 20-of-29   4.5 GB: 21-of-29   4.5 GB: 22-of-29   4.7 GB: 23-of-29   4.5 GB: 24-of-29   4.5 GB: 25-of-29   4.7 GB: 26-of-29   4.5 GB: 27-of-29   4.5 GB: 28-of-29   3.7 GB: 29-of-29
Model ArchitectureQwen2ForCausalLM
Context Length40960
Model Max Length40960
Transformers Version4.48.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Kevin 32B

Best Alternatives
Context / RAM
Downloads
Likes
Openbuddy Qwq 32B V24.2 200K195K / 65.8 GB193
Openbuddy Qwq 32B V24.1 200K195K / 65.8 GB123
Openbuddy Qwq 32B V25.2q 200K195K / 65.8 GB104
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB82
DeepSeek R1 Distill Qwen 32B128K / 65.7 GB9908151531
Qwen2.5 32B128K / 65.5 GB239028174
Baichuan M2 32B128K / 65.8 GB110798120
OpenReasoning Nemotron 32B128K / 65.8 GB143528123
Brahmastra 0.2128K / 65.9 GB4900
K2 Think128K / 65.8 GB3935360
Note: green Score (e.g. "73.2") means that the model is better than cognition-ai/Kevin-32B.

Rank the Kevin 32B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52922 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer