invokeable()
← directory / models / llama-3-1-nemotron-ultra-253b

Llama 3.1 Nemotron Ultra 253B

model llama-3-1-nemotron-ultra-253b

Draft entry — numbers not yet verified against primary sources.

128K
context
8K
max output
—
input
—
output
—
knowledge cutoff
weights
no API yet

01Providers

No API offering captured yet — this entry exists for coverage. The sources below point at the weights and official docs; tell us if a provider serves it.

02Related

Llama 3.3 Nemotron Super 49B v1.52025-07Llama 3.1 Nemotron 70B Instruct2025-04Llama 3.3 Nemotron Super 49B v12025-04Llama 4 Maverick2025-04Llama 4 Maverick 17B Instruct2025-04Llama 4 Scout2025-04

03Sources · where these numbers come from

  1. https://github.com/sst/models.dev
  2. https://docs.api.nvidia.com/nim/
  3. https://huggingface.co/nvidia
  4. https://huggingface.co/models?search=llama-3-1-nemotron-ultra-253b