NVIDIA-Nemotron-Nano-12B-v2-GGUF

Home/Models/Mungert/NVIDIA-Nemotron-Nano-12B-v2-GGUF

Mungert/NVIDIA-Nemotron-Nano-12B-v2-GGUF

kind: gguf
quant: gguf (16-bit)
family: nemotron
modality: text-generation
root model: nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base
provider: Mungert
license: other
language: en, es, fr, de, it, ja
context: 128K
library: transformers
vRAM (GB): —
size on disk: —
downloads: 315
likes: 2
created: —
last modified: 2025-09-24T15:44:56+00:00 (2025)
huggingface: https://huggingface.co/Mungert/NVIDIA-Nemotron-Nano-12B-v2-GGUF
tags: transformersggufnvidiapytorchtext-generationenesfrdeitjadataset:nvidia/Nemotron-Post-Training-Dataset-v1dataset:nvidia/Nemotron-Post-Training-Dataset-v2dataset:nvidia/Nemotron-Pretraining-Dataset-sampledataset:nvidia/Nemotron-CC-v2dataset:nvidia/Nemotron-CC-Math-v1dataset:nvidia/Nemotron-Pretraining-SFT-v1arxiv:2504.03624arxiv:2508.14444arxiv:2412.02595base_model:nvidia/NVIDIA-Nemotron-Nano-12B-v2-Basebase_model:quantized:nvidia/NVIDIA-Nemotron-Nano-12B-v2-Baselicense:otherendpoints_compatible

benchmark	category	score	context	conf	evidence
MATH-500	math	97.75	MATH500	medium	`\| MATH500 \| 97.75% \|`
IFEval	instruction-following	89.81	IFEVAL-Instruction	medium	`\| IFEVAL-Instruction \| 89.81% \|`
IFEval	instruction-following	84.7	IFEVAL-Prompt	medium	`\| IFEVAL-Prompt \| 84.70% \|`
AIME 2025	math	76.25	AIME25	medium	`\| AIME25 \| 76.25% \|`
BFCL (function calling)	agentic	66.98	BFCL v3	medium	`\| BFCL v3 \| 66.98% \|`
GPQA	reasoning	64.48	GPQA	medium	`\| GPQA \| 64.48% \|`

none scraped.