Home / Models / Nemotron 3 Nano 30B A3B
NVIDIA

Nemotron 3 Nano 30B A3B

Nemotron 3 Nano 30B A3B is an open-weights 30B-parameter model by NVIDIA. It holds an Intelligence score of 42.4 on the local.ai leaderboard (2026-08 snapshot).

MoEopen weights
42.4
local.ai Intelligence
Parameters
30B
MoE · 3B active parameters
Benchmarks (local.ai snapshot)
τ²-bench
39%
GAIA
46%
GDPval
41%
HuggingFace metadata · updated 2026-07-23
repo
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
license
other
downloads
991,069
likes
811
Official HuggingFace repoOllamaCompare on the savings tool

Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.

Does it fit your hardware?

Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.

Q4_K_M 17.4GQ6_K 27GQ8_0 33GFP16 60G
Quantization≈ File sizeNote
IQ2_XXS8.1 GBExtreme compression, largest quality loss
IQ3_XXS10.8 GBVery small
Q3_K_M13.8 GBSmall
NVFP415 GBNVIDIA 4-bit
Q4_K_S16.2 GBCommon
Q4_K_M17.4 GBMost common sweet spot
Q5_K_M22.8 GBBalanced
Q6_K27 GBNear-lossless
Q8_033 GBNear-lossless
FP1660 GBOriginal weights

Actual files on HuggingFace

FileSize
model-00006-of-00013.safetensors4.66 GB
model-00012-of-00013.safetensors4.65 GB
model-00004-of-00013.safetensors4.65 GB
model-00009-of-00013.safetensors4.65 GB
model-00011-of-00013.safetensors4.65 GB
model-00008-of-00013.safetensors4.65 GB
GGUF: lmstudio-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF · 62,148 downloads
FileSize
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q4_K_M.gguf22.83 GBdownload
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q6_K.gguf31.21 GBdownload
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q8_0.gguf31.28 GBdownload
mmproj-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16.gguf1.48 GBdownload
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF · 15,789 downloads
FileSize
BF16/Nemotron-3-Nano-30B-A3B-BF16-00001-of-00002.gguf46.49 GBdownload
BF16/Nemotron-3-Nano-30B-A3B-BF16-00002-of-00002.gguf12.35 GBdownload
Nemotron-3-Nano-30B-A3B-IQ4_NL.gguf16.93 GBdownload
Nemotron-3-Nano-30B-A3B-IQ4_XS.gguf16.92 GBdownload
Nemotron-3-Nano-30B-A3B-Q2_K_L.gguf16.85 GBdownload
Nemotron-3-Nano-30B-A3B-Q3_K_M.gguf18.63 GBdownload
Nemotron-3-Nano-30B-A3B-Q3_K_S.gguf16.88 GBdownload
Nemotron-3-Nano-30B-A3B-Q4_0.gguf16.96 GBdownload
Nemotron-3-Nano-30B-A3B-Q4_1.gguf18.68 GBdownload
Nemotron-3-Nano-30B-A3B-Q4_K_M.gguf22.89 GBdownload
Nemotron-3-Nano-30B-A3B-Q4_K_S.gguf20.51 GBdownload
Nemotron-3-Nano-30B-A3B-Q5_K_M.gguf24.35 GBdownload

What you save self-hosting this model

Uses the model's own API price when it exists; otherwise the closest commercial equivalent.

Waiting for hardware detection…

Related models

NVIDIA
Nemotron 3.5 Lightning
Intelligence 65.5
NVIDIA
Nemotron 3 Super 120B A12B
120B params · Intelligence 64.6
NVIDIA
Nemotron 3 Nano Omni 30B A3B Reasoning
30B params · Intelligence 34.1
NVIDIA
Llama 3.1 Nemotron 70B
70B params · not yet scored

RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.