Home / Models / Nemotron 3.5 Lightning
NVIDIA

Nemotron 3.5 Lightning

Nemotron 3.5 Lightning is an open-weights model by NVIDIA. It holds an Intelligence score of 65.5 on the local.ai leaderboard (2026-08 snapshot).

open weights
65.5
local.ai Intelligence
Parameters
undisclosed
Benchmarks (local.ai snapshot)
τ²-bench
62%
GAIA
68%
GDPval
65%
HuggingFace metadata · updated 2026-08-13
repo
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
license
other
downloads
62,965
likes
147
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.

Params not disclosed — no size estimate.

Actual files on HuggingFace

FileSize
model-00012-of-00014.safetensors4.65 GB
model-00004-of-00014.safetensors4.65 GB
model-00009-of-00014.safetensors4.65 GB
model-00011-of-00014.safetensors4.65 GB
model-00008-of-00014.safetensors4.65 GB
model-00010-of-00014.safetensors4.65 GB
GGUF: unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · 79,108 downloads
FileSize
BF16/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16-00001-of-00002.gguf45.81 GBdownload
BF16/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16-00002-of-00002.gguf15.52 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MXFP4_MOE.gguf21.62 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q8_0.gguf32.60 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-IQ1_M.gguf18.09 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-IQ2_M.gguf18.10 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-IQ2_XXS.gguf18.09 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-IQ3_S.gguf19.70 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-IQ3_XXS.gguf18.40 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-IQ4_NL.gguf19.78 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-Q3_K_XL.gguf19.78 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-Q4_K_M.gguf23.53 GBdownload
GGUF: ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · 63,847 downloads
FileSize
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16.gguf58.84 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_0.gguf17.60 GBdownload
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q8_0.gguf31.28 GBdownload
mtp-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16.gguf3.81 GBdownload
mtp-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_0.gguf1.08 GBdownload
mtp-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q8_0.gguf2.03 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 Super 120B A12B
120B params · Intelligence 64.6
NVIDIA
Nemotron 3 Nano 30B A3B
30B params · Intelligence 42.4
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.