NVIDIA-Nemotron-3-Nano-4B-GGUF

Home/Models/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF

unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF

kind: gguf
quant: gguf (16-bit)
family: nemotron
modality: text-generation
root model: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
provider: unsloth
license: other
language: en
context: 262K
library: —
vRAM (GB): —
size on disk: —
downloads: 5,749
likes: 79
created: —
last modified: 2026-03-17T00:16:31+00:00 (2026)
huggingface: https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF
tags: ggufnvidiapytorchtext-generationenarxiv:2511.16664arxiv:2504.03624arxiv:2512.20856arxiv:2512.20848arxiv:2412.02595base_model:nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16base_model:quantized:nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16license:otherendpoints_compatibleregion:usconversational

benchmark	category	score	context	conf	evidence
MATH-500	math	95.4	MATH500	medium	`\| MATH500 \| 95.4 \|`
IFEval	instruction-following	92.0	IFEVAL-Instruction	medium	`\| IFEVAL-Instruction \| 92 \|`
RULER	long-context	91.1	RULER (128k)	medium	`\| RULER (128k) \| 91.1 \|`
IFEval	instruction-following	88.0	IFEval-Instruction	medium	`\| IFEval-Instruction \| 88 \|`
IFEval	instruction-following	87.9	IFEVAL-Prompt	medium	`\| IFEVAL-Prompt \| 87.9 \|`
IFEval	instruction-following	82.8	IFEval-Prompt	medium	`\| IFEval-Prompt \| 82.8 \|`
AIME 2025	math	78.5	AIME25	medium	`\| AIME25 \| 78.5 \|`
BFCL (function calling)	agentic	61.1	BFCL v3	medium	`\| BFCL v3 \| 61.1 \|`
GPQA	reasoning	53.2	GPQA	medium	`\| GPQA \| 53.2 \|`
IFBench	instruction-following	44.2	IFBench-Instruction	medium	`\| IFBench-Instruction \| 44.2 \|`
IFBench	instruction-following	43.2	IFBench-Prompt	medium	`\| IFBench-Prompt \| 43.2 \|`

none scraped.