K2 by LLM360

 »  All LLMs  »  LLM360  »  K2   URL Share it on

K2 is an open-source language model by LLM360. Features: 65.3b LLM, VRAM: 131.7GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.19, Arc: 64, HellaSwag: 85.7, MMLU: 68, GSM8K: 48.7.

  En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LLM360/K2 

K2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

K2 Parameters and Internals

Model Type 
text-generation
Supported Languages 
en (proficient)
Training Details 
Data Sources:
dm-math, pubmed-abstracts, uspto, pubmed-central, redpajama.arxiv, starcoder.spm, starcoder.fim, redpajama.stackexchange, starcoder, pile-of-law, redpajama.book, s2orc, redpajama.wikipedia, refinedweb
Data Volume:
1.4T tokens
LLM NameK2
Repository 🤗https://huggingface.co/LLM360/K2 
Model Size65.3b
Required VRAM131.7 GB
Updated2026-05-09
MaintainerLLM360
Model Typellama
Model Files  4.7 GB: 1-of-27   4.9 GB: 2-of-27   4.9 GB: 3-of-27   4.9 GB: 4-of-27   4.9 GB: 5-of-27   4.9 GB: 6-of-27   4.9 GB: 7-of-27   4.9 GB: 8-of-27   4.9 GB: 9-of-27   4.9 GB: 10-of-27   4.9 GB: 11-of-27   4.9 GB: 12-of-27   4.9 GB: 13-of-27   4.9 GB: 14-of-27   4.9 GB: 15-of-27   4.9 GB: 16-of-27   4.9 GB: 17-of-27   4.9 GB: 18-of-27   4.9 GB: 19-of-27   4.9 GB: 20-of-27   4.9 GB: 21-of-27   4.9 GB: 22-of-27   4.9 GB: 23-of-27   4.9 GB: 24-of-27   4.9 GB: 25-of-27   4.9 GB: 26-of-27   4.5 GB: 27-of-27
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Vocabulary Size32032
Torch Data Typefloat16

Best Alternatives to K2

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text 512K512K / 13.5 GB132
LWM Text Chat 512K512K / 13.5 GB112
LWM Text 256K256K / 13.5 GB123
LWM Text Chat 256K256K / 13.5 GB103
Pallas 0.5 LASER 0.1195K / 68.9 GB10402
Veena128K / 7.6 GB3406232
SnorTTS Indic V0128K / 9.5 GB7721
Llama 3.1 Medprm Reward V1.0128K / 16.1 GB66716
Orpheus AUS128K /  GB50
Finetuning Health Ci128K / 6.5 GB32
Note: green Score (e.g. "73.2") means that the model is better than LLM360/K2.

Rank the K2 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? 53999 in total.

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