Description

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.

Technical Specifications

Example API Call

curl -X POST https://api.neuralhub.xyz/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer NEURALHUB_API_KEY" \
-d '{
  "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "" }
  ],
  "temperature": 0.7,
  "max_tokens": 500,
  "top_p": 0.9
}'

Response Format

The API returns an OpenAI-compatible response. Example:

{
  "id": "chatcmpl-<uuid>",
  "object": "chat.completion",
  "created": 1765590371,
  "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The answer to life, the universe, and everything is famously 42..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 26,
    "completion_tokens": 169,
    "total_tokens": 195
  }
}