Llama 3.3 Nemotron Super 49B V1.5

About Llama 3.3 Nemotron Super 49B V1.5

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 multi-turn chat, followed by multiple RL stages; Reward-aware Preference Optimization (RPO) for alignment, RL with Verifiable Rewards (RLVR) for step-wise reasoning, and iterative DPO to refine tool-use behavior. A distillation-driven Neural Architecture Search (“Puzzle”) replaces some attention blocks and varies FFN widths to shrink memory footprint and improve throughput, enabling single-GPU (H100/H200) deployment while preserving instruction following and CoT quality. In internal evaluations (NeMo-Skills, up to 16 runs, temp = 0.6, top_p = 0.95), the model reports strong reasoning/coding results, e.g., MATH500 pass@1 = 97.4, AIME-2024 = 87.5, AIME-2025 = 82.71, GPQA = 71.97, LiveCodeBench (24.10–25.02) = 73.58, and MMLU-Pro (CoT) = 79.53. The model targets practical inference efficiency (high tokens/s, reduced VRAM) with Transformers/vLLM support and explicit “reasoning on/off” modes (chat-first defaults, greedy recommended when disabled). Suitable for building agents, assistants, and long-context retrieval systems where balanced accuracy-to-cost and reliable tool use matter.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

NVIDIA Model Lineup

Compare all models from NVIDIA to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

GPT-4.1 Nano

OpenAI

Input: $0.10

Output: $0.40

Context: 1.0M

Gemini 2.0 Flash

Google

Input: $0.10

Output: $0.40

Context: 1.0M

Gemini 2.5 Flash Lite Preview 09-2025

Google

Input: $0.10

Output: $0.40

Context: 1.0M

Mistral Tiny

Mistral

Input: $0.25

Output: $0.25

Context: 32k

💡 Cheaper Alternatives

Same Brand (NVIDIA)

Cross Brand

🚀 Quick Start

Get started with Llama 3.3 Nemotron Super 49B V1.5 API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision