When was Llama-3.3 Nemotron Super 49B v1 released?

Llama-3.3 Nemotron Super 49B v1 was released on March 18, 2025 by Nvidia. This is the official Llama-3.3 Nemotron Super 49B v1 release date tracked on LLM Stats.

How big is Llama-3.3 Nemotron Super 49B v1?

Llama-3.3 Nemotron Super 49B v1 has 49.9 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Llama-3.3 Nemotron Super 49B v1?

Llama-3.3 Nemotron Super 49B v1 was created by Nvidia.

What is the license for Llama-3.3 Nemotron Super 49B v1?

Llama-3.3 Nemotron Super 49B v1 is released under the Llama 3.1 Community License license. This is an open-source / open-weight license that permits self-hosting.

What is the knowledge cutoff date for Llama-3.3 Nemotron Super 49B v1?

Llama-3.3 Nemotron Super 49B v1 has a knowledge cutoff of December 2023, meaning it was trained on data up to that point and may not know about events after it.

Where is the Llama-3.3 Nemotron Super 49B v1 paper or technical report?

Llama-3.3 Nemotron Super 49B v1 has a paper or technical report available at https://arxiv.org/abs/2502.00203. Use that source for architecture, training, release and evaluation details.

What models should I compare Llama-3.3 Nemotron Super 49B v1 against?

Common Llama-3.3 Nemotron Super 49B v1 comparisons include Llama-3.3 Nemotron Super 49B v1 vs Kimi-k1.5, Llama-3.3 Nemotron Super 49B v1 vs Qwen3 14B, Llama-3.3 Nemotron Super 49B v1 vs MiMo-V2.5-Pro. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.

Llama-3.3 Nemotron Super 49B v1 Benchmarks, Pricing & Context Window

Name: Llama-3.3 Nemotron Super 49B v1
Author: Nvidia

Llama-3.3 Nemotron Super 49B v1: Benchmarks, Pricing & Context Window

Llama-3.3 Nemotron Super 49B v1 is a language model from Nvidia, released in March 2025.

Llama-3.3-Nemotron-Super-49B-v1 is a large language model (LLM) derived from Meta Llama-3.3-70B-Instruct. It's post-trained for reasoning, chat, RAG, and tool calling, offering a balance between accuracy and efficiency (optimized for

Llama-3.3 Nemotron Super 49B v1 benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Llama-3.3 Nemotron Super 49B v1 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Llama-3.3 Nemotron Super 49B v1 holds up as conversations get longer.

Quality Tracker

Llama-3.3 Nemotron Super 49B v1 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Mon Oct 05 2026

Notice missing or incorrect data?

Llama-3.3 Nemotron Super 49B v1 model size

Llama-3.3 Nemotron Super 49B v1 has 49.9 billion parameters. See how it compares to other models in the same parameter range.

Parameters

49.9B

Large (30–80B)

49.9B

1B7B70B405B

Try now

huggle

Llama-3.3 Nemotron Super 49B v1in Huggle

Make it with
Llama-3.3 Nemotron Super 49B v1.

Llama-3.3 Nemotron Super 49B v1 latency

Llama-3.3 Nemotron Super 49B v1 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Llama-3.3 Nemotron Super 49B v1 examples

Recent arena outputs from Llama-3.3 Nemotron Super 49B v1, picked from the highest-ranked matchups.

Llama-3.3 Nemotron Super 49B v1 license

Llama-3.3 Nemotron Super 49B v1 is released under the Llama 3.1 Community License license, which restricts commercial use, has 49.9B parameters, has a knowledge cutoff of December 2023.

License: Llama 3.1 Community License; Non-commercial
Parameters: 49.9B
Knowledge cutoff: December 2023

Llama-3.3 Nemotron Super 49B v1 resources

Official sources for Llama-3.3 Nemotron Super 49B v1: official playground, paper or system card, official launch post, model weights.

Llama-3.3 Nemotron Super 49B v1 vs other models

The most-compared alternatives to Llama-3.3 Nemotron Super 49B v1 are Kimi-k1.5, Qwen3 14B, MiMo-V2.5-Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.