nemotron-3-nano:4b-mlx

922.2K yesterday

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

tools thinking cloud 4b 30b 
ollama run nemotron-3-nano:4b-mlx

Details

yesterday

87e6cab38edd · 2.9GB

json
{ "_from_model_config": true, "bos_token_id": 1, "eos_token_id": [ 2, 11 ], "pad_token_id": 0, "temp
json
{ "producer": { "name": "modelopt", "version": "0.0.0" }, "quantization": { "quant_algo": "MIXED_PRE
json
{ "bos_token": { "content": "<s>", "lstrip": false, "normalized": false, "rstrip": false, "single_wo
json
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<u
json
{ "add_bos_token": false, "add_eos_token": false, "add_prefix_space": false, "added_tokens_decoder":
license
NVIDIA Open Model License Agreement Last Modified: October 24, 2025 This NVIDIA Open Model License A
params
{ "temperature": 1, "top_p": 0.95 }
json
{ "architectures": [ "NemotronHForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "h
template
{{ .Prompt }}
271 tensors

Readme

Nemotron-3-Nano

Nemotron 3 Nano 4B

ollama run nemotron-3-nano:4b

Nemotron 3 Nano 30B

ollama run nemotron-3-nano:30b

Ollama’s Cloud

ollama run nemotron-3-nano:30b-cloud

What is Nemotron?

NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents.

Nemotron 3 Nano is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model’s reasoning capabilities can be configured through a flag in the chat template. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks.

The model employs a hybrid Mixture-of-Experts (MoE) architecture, consisting of 23 Mamba-2 and MoE layers, along with 6 Attention layers. Each MoE layer includes 128 experts plus 1 shared expert, with 6 experts activated per token. The model has 3.5B active parameters and 30B parameters in total.

The supported languages include: English, German, Spanish, French, Italian, and Japanese. Improved using Qwen.

License/Terms of Use

Governing Terms: Use of this model is governed by the NVIDIA Open Model License Agreement.