Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

Nemotron Reasoning LoRA Adapter

LoRA adapter for nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 / compatible Nemotron-3-Nano-30B-A3B base model.

Expected files:

  • adapter_config.json
  • adapter_model.safetensors

RunPod download example:

bash
hf download PhuQuy23TNT1/nemotron-reasoning-lora-adapter \
  --local-dir /workspace/nemotron-reasoning-lora-adapter

Rollout example:

bash
python offline/sample_rollouts.py \
  --model_path unsloth/Nemotron-3-Nano-30B-A3B \
  --adapter_path /workspace/nemotron-reasoning-lora-adapter \
  --mode probe \
  --output /workspace/rollouts.jsonl

Model provider

PhuQuy23TNT1

Model tree

Base

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Adapter

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Model card

Explore FriendliAI today

Get startedTalk to an engineer