rnogy/Nvidia_Llama-3_3-Nemotron-Super-49B-v1

rnogy/ Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5

328 Downloads Updated 3 months ago

Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model which is a derivative of Meta Llama-3.3-70B-Instruct. It is a reasoning model that is post trained for reasoning, human chat preferences, and agentic tasks, such as RAG and tool calling.

ollama run rnogy/Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5

curl http://localhost:11434/api/chat \
  -d '{
    "model": "rnogy/Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='rnogy/Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'rnogy/Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

4 models

Size

Context

Input

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:latest

100GB · 128K context window · Text · 3 months ago

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:latest

100GB

128K

Text

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:q3_K_M

24GB · 128K context window · Text · 3 months ago

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:q3_K_M

24GB

128K

Text

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:q4_K_M

30GB · 128K context window · Text · 3 months ago

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:q4_K_M

30GB

128K

Text

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:q8_0

53GB · 128K context window · Text · 3 months ago

Nvidia_Llama-3_3-Nemotron-Super-49B-v1_5:q8_0

53GB

128K

Text

Readme

Just Llama-3_3-Nemotron-Super-49B-v1_5 converted to gguf and quantized as is.