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

Text Generation • Updated 18 days ago • 225k • 1.58k

Note Best overall model

Qwen/Qwen2.5-72B-Instruct

Text Generation • Updated Sep 25 • 417k • • 452

Note Current best for Japanese translation

google/gemma-2-27b-it

Text Generation • Updated Aug 27 • 247k • 438

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 • 103k • 120

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 23 days ago • 58 • 1

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