Llama 3_3 Nemotron Super 49B V 1_5
Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model (LLM) optimized for advanced reasoning, conversational interactions, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta's Llama-3.3-70B-Instruct, it employs a Neural Architecture Search (NAS) approach, significantly enhancing efficiency and reducing memory requirements.
Input
Output
Context
131K
Max Output
16K
Parameters
49B
Technical Specifications
Model TypeChat
Context Window131K
Max Output Tokens16K
Parameters49B
Training Cutoff—
Licenseother
Capabilities
Input Modalities
text
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generation
Benchmarks
#75
Rank (Text)
+11/-11
arena text ci 95
1309
Arena Score (Text)
2,371
Votes (Text)
Resources & Links
Estimated GPU Requirements for Llama 3_3 Nemotron Super 49B V 1_5
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.