Llama 3.1 Nemotron Ultra 253B v1
Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency.
Input
Output
Context
131K
Max Output
—
Parameters
253B
Technical Specifications
Model TypeChat
Context Window131K
Max Output Tokens—
Parameters253B
Training Cutoff—
License—
Capabilities
Input Modalities
text
Output Modalities
text
Features
code_generationfunction_callingjson_modereasoningstreamingtext_generation
Benchmarks
Chatbot Arena
#65
Rank (Text)
+11/-11
arena text ci 95
1320
Arena Score (Text)
2,656
Votes (Text)
Artificial Analysis
8.1%
HLE
74.7%
AIME
72.8%
GPQA
34.7%
SciCode
95.2%
MATH 500
82.5%
MMLU Pro
63.7
Math
13.1
Coding
64.1%
LiveCodeBench
15.0
Intelligence
41.9
Speed (tok/s)
48.5
TTFA (s)
0.735
TTFT (s)
Resources & Links
Estimated GPU Requirements for Llama 3.1 Nemotron Ultra 253B v1
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.