nvidia / text-generation updated 8 months ago

NVIDIA-Nemotron-Nano-12B-v2

Name: NVIDIA-Nemotron-Nano-12B-v2
Author: nvidia

NVIDIA-Nemotron-Nano-12B-v2 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 controlled via a system prompt. If the user prefers the model to provide its final answer w...

Params

12.3 B

Context

—

Downloads 30d

364 K

Likes

164

Licence: other Not gated SAFETENSORS 6 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

397 K364 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	24.6 GB	29.4 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/nvidia-nemotron-nano-12b-v2
{
  "hf_id": "nvidia/NVIDIA-Nemotron-Nano-12B-v2",
  "params_b": 12.31,
  "context_length": null,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 363704,
  "vram_estimates": [
    { "quant": "bf16", "gb": 29.4 }
  ],
  "updated_at": "2026-07-28T18:05:52Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Parameters: 12.3 B
Tensor type: BF16
Licence: other
First seen on the Hub: 2025-08-21
Training datasets: nvidia/Nemotron-Post-Training-Dataset-v1, nvidia/Nemotron-Post-Training-Dataset-v2, nvidia/Nemotron-Pretraining-Dataset-sample, nvidia/Nemotron-CC-v2, nvidia/Nemotron-CC-Math-v1, nvidia/Nemotron-Pretraining-SFT-v1
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M Llama-3.1-8B-Instruct 8.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB