nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Text Generation • Updated 28 days ago • 216k • 1.7k

Note Best overall model

Qwen/Qwen2.5-72B-Instruct

Text Generation • Updated Sep 25 • 470k • • 486

Note Current best for Japanese translation

google/gemma-2-27b-it

Text Generation • Updated Aug 27 • 228k • 445

Note Really nice mix of speed and intelligence, somewhat good in Japanese but mixed results maybe

princeton-nlp/gemma-2-9b-it-SimPO

Text Generation • Updated Aug 2 • 107k • 124

Note Current best fast model, sometimes will become weird and spit out random stuff not in English but overall good. Great world knowledge for size, somewhat poor coding(?) and low context but still good for RAG

nonetrix/llama-3.1-70B-lumitron

Text Generation • Updated Oct 20 • 14 • 1

Note Best roleplay model I have personally used, better might exist