Llama 3.3 Nemotron Super 49B V1.5

NVIDIA · nvidia/llama-3.3-nemotron-super-49b-v1.5

← Back to leaderboard

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...

open weightstexttext->text

Context

Max context: 131072
Max output: 16384

Pricing

Input / 1M: 0.40
Output / 1M: 0.40
Blend / 1M: 0.40

Quality

Quality index:

Provider

Provider: NVIDIA
Moderated: no