NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16

Home/Models/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16

NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16

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

kind: original
quant: bf16 (16-bit)
family: nemotron
modality: text-generation
root model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16
provider: nvidia
license: other
language: en, es, fr, de, ja, it, pt, zh, ar, da, ko, nl
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 72,272
likes: 129
created: —
last modified: 2026-03-15T04:27:40+00:00 (2026)
huggingface: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16
tags: transformerssafetensorsnvidiapytorchtext-generationenesfrdejaitptzhardakonlplrusvthdataset:nvidia/Nemotron-Pretraining-Code-v1dataset:nvidia/Nemotron-CC-v2dataset:nvidia/Nemotron-Pretraining-SFT-v1

Benchmark scores (19)

benchmark	category	score	context	conf	evidence
ARC-Challenge	knowledge	94.45	ARC-Challenge (25-shot, acc_norm)	medium	`\| ARC-Challenge (25-shot, acc_norm) \| 94.45 \| 91.89 \|`
GSM8K	math	89.01	GSM8K (8-shot, acc)	medium	`\| GSM8K (8-shot, acc) \| 89.01 \| 92.34 \|`
HellaSwag	knowledge	83.14	HellaSwag (10-shot, acc_norm)	medium	`\| HellaSwag (10-shot, acc_norm) \| 83.14 \| 85.56 \|`
MGSM	math	82.53	MGSM (8-shot, avg acc)	medium	`\| MGSM (8-shot, avg acc) \| 82.53 \| 83.00 \|`
MMLU	knowledge	81.07	MMLU (5-shot, acc)	medium	`\| MMLU (5-shot, acc) \| 81.07 \| 78.56 \|`
PIQA	knowledge	81.01	PIQA (0-shot, acc_norm)	medium	`\| PIQA (0-shot, acc_norm) \| 81.01 \| 84.33 \|`
WinoGrande	knowledge	78.22	WinoGrande (5-shot, acc)	medium	`\| WinoGrande (5-shot, acc) \| 78.22 \| 79.64 \|`
MMLU	knowledge	76.84	MMLU Global Lite (5-shot, avg acc)	medium	`\| MMLU Global Lite (5-shot, avg acc) \| 76.84 \| 74.47 \|`
RULER	long-context	75.44	RULER (256K, 0-shot, acc)	medium	`\| RULER (256K, 0-shot, acc) \| Not Supported \| 75.44 \|`
MBPP	coding	73.15	MBPP-Sanitized (3-shot)	medium	`\| MBPP-Sanitized (3-shot) \| 73.15 \| 75.49 \|`
HumanEval	coding	70.73	HumanEval (0-shot)	medium	`\| HumanEval (0-shot) \| 70.73 \| 78.05 \|`
RULER	long-context	70.56	RULER (512K, 0-shot, acc)	medium	`\| RULER (512K, 0-shot, acc) \| Not Supported \| 70.56 \|`
RULER	long-context	63.55	RULER (64K, 0-shot, acc)	medium	`\| RULER (64K, 0-shot, acc) \| 63.55 \| 87.50 \|`
AGIEval	reasoning	63.12	AGIEval-En (3/5-shot, CoT acc)	medium	`\| AGIEval-En (3/5-shot, CoT acc) \| 63.12 \| 68.32 \|`
MMLU-Pro	knowledge	61.71	MMLU-Pro (5-shot, CoT EM)	medium	`\| MMLU-Pro (5-shot, CoT EM) \| 61.71 \| 65.05 \|`
MATH	math	61.14	MATH (4-shot, acc)	medium	`\| MATH (4-shot, acc) \| 61.14 \| 82.88 \|`
RULER	long-context	60.69	RULER (128K, 0-shot, acc)	medium	`\| RULER (128K, 0-shot, acc) \| 60.69 \| 82.92 \|`
MATH-500	math	55.08	MATH-500 (4-shot, avg@32)	medium	`\| MATH-500 (4-shot, avg@32) \| 55.08 \| 78.63 \|`
OpenBookQA	knowledge	44.8	OpenBookQA (0-shot, acc_norm)	medium	`\| OpenBookQA (0-shot, acc_norm) \| 44.80 \| 46.20 \|`

Discussions (0)

none scraped.