AI PLATFORMS & MODELS
OPEN WEIGHTSOPEN SOURCE SELF-HOSTABLE

Nemotron 70B

by NVIDIA

RLHF-tuned open model from NVIDIA.

77HYLAND SCORE
1.5k views this week
Try Nemotron 70B
SHARE Post on X LinkedIn

Overview

Llama-3.1-Nemotron-70B is NVIDIA’s reward-model-tuned derivative of Llama, topping alignment leaderboards at release. Open weights with an NVIDIA license, tuned for helpfulness in chat applications.

Key features

  • Tuned with NVIDIA reward models
  • Strong Arena Hard alignment scores
  • 128K context window
  • NIM microservice deployment
  • Open weights

Tags

Self-HostRLHFChatNVIDIA

Related in AI Platforms & Models

FEATURED VERIFIED

DeepSeek R1

DeepSeek
93HYLAND

Open-weight reasoning that rivals the frontier.

Open WeightsOpen Source Self-host
15.3k/wk
View
VERIFIED
92HYLAND

Self-hosted AI, privacy-critical apps

Open WeightsOpen Source Self-host
View
FEATURED VERIFIED

Kimi K2

Moonshot AI
91HYLAND

Open trillion-parameter agentic intelligence.

Open WeightsOpen Source Self-host
12.8k/wk
View