NVIDIA/Mixture of Experts

Nemotron 3.5 Lightning 30B-A3B

Name: Nemotron 3.5 Lightning 30B-A3B
Author: NVIDIA

Nemotron 3.5 Lightning 30B-A3B — NVIDIA's sparse 30B with 3B active per token, built for throughput on a single card.

chatcodingreasoningmultilingualtool_use

31.58B

Parameters (3B active)

256K

Context length

Benchmarks

Quantizations

66K

HF downloads

Architecture

MoE

Released

2026-08-11

Layers

KV Heads

Head Dim

128

Family

nemotron

Quantization Options

Context length:

Quant	Bits	VRAM @ 16K	Quality
IQ3_XXS	3.25	13.9 GB 13.3 + 0.6 KV	low
IQ3_XS	3.5	14.9 GB 14.3 + 0.6 KV	low
Q3_K_S	3.64	15.5 GB 14.9 + 0.6 KV	low
IQ3_M	3.76	15.9 GB 15.3 + 0.6 KV	low
Q3_K_M	4	16.9 GB 16.3 + 0.6 KV	low
Q3_K_L	4.3	18.1 GB 17.5 + 0.6 KV	moderate
IQ4_XS	4.46	18.7 GB 18.1 + 0.6 KV	moderate
Q4_K_S	4.67	19.5 GB 18.9 + 0.6 KV	moderate
Q4_K_M	4.89	20.4 GB 19.8 + 0.6 KV	good
Q5_K_S	5.57	23.1 GB 22.5 + 0.6 KV	good
Q5_K_M	5.7	23.6 GB 23.0 + 0.6 KV	good
Q6_K	6.56	27.0 GB 26.4 + 0.6 KV	excellent
Q8_0	8.5	34.7 GB 34.0 + 0.6 KV	lossless
FP16	16	64.3 GB 63.6 + 0.6 KV	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN NEMOTRON 3.5 LIGHTNING 30B-A3B NOW

Rent on Vast.ai →Or RunPod →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (6)

GPQA Diamond74.3

AA Long Context55.3

SciCode31.6

AA Coding26.8

AA Intelligence23.6

HLE10.6

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run nemotron:32b-q4_K_M

Tag may need adjustment — check ollama.com/library/nemotron for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

AMD RX 7900 XT

20 GB VRAM • 800 GB/s

AMD

$849

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4000 Ada 20GB

20 GB VRAM • 432 GB/s

NVIDIA

$1250

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA A10M

20 GB VRAM • 500 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce RTX 3080 Ti 20 GB

20 GB VRAM • 760 GB/s

NVIDIA

$1199

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 7900 XT

20 GB VRAM • 800 GB/s

AMD

$899

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4000 Ada Generation

20 GB VRAM • 360 GB/s

NVIDIA

$1250

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4000 SFF Ada Generation

20 GB VRAM • 280 GB/s

NVIDIA

$1250

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX A4500

20 GB VRAM • 640 GB/s

NVIDIA

$2000

NVIDIA RTX 4090

24 GB VRAM • 1008 GB/s

NVIDIA

$1599

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 3090 Ti

24 GB VRAM • 1008 GB/s

NVIDIA

$999

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 3090

24 GB VRAM • 936 GB/s

NVIDIA

$850

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD RX 7900 XTX

24 GB VRAM • 960 GB/s

AMD

$999

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Apple M4 Pro (24GB)

24 GB VRAM • 273 GB/s

APPLE

$1399

NVIDIA L4 24GB

24 GB VRAM • 300 GB/s

NVIDIA

$2500

NVIDIA A10 24GB

24 GB VRAM • 600 GB/s

NVIDIA

$3500

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Apple M2 (24GB)

24 GB VRAM • 100 GB/s

APPLE

$999

Apple M3 (24GB)

24 GB VRAM • 100 GB/s

APPLE

$999

Apple M4 (24GB)

24 GB VRAM • 120 GB/s

APPLE

$699

NVIDIA Tesla M40 24 GB

24 GB VRAM • 288 GB/s

NVIDIA

NVIDIA Tesla P10

24 GB VRAM • 694 GB/s

NVIDIA

NVIDIA Tesla P40

24 GB VRAM • 347 GB/s

NVIDIA

NVIDIA Quadro RTX 6000

24 GB VRAM • 672 GB/s

NVIDIA

$4000

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA Quadro RTX 6000 Passive

24 GB VRAM • 624 GB/s

NVIDIA

$4000

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce RTX 3090

24 GB VRAM • 936 GB/s

NVIDIA

$1499

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA A10 PCIe

24 GB VRAM • 600 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA A10G

24 GB VRAM • 600 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX A5000

24 GB VRAM • 768 GB/s

NVIDIA

$2500

NVIDIA GeForce RTX 3090 Ti

24 GB VRAM • 1010 GB/s

NVIDIA

$1999

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce RTX 4090

24 GB VRAM • 1010 GB/s

NVIDIA

$1599

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA L40 CNX

24 GB VRAM • 864 GB/s

NVIDIA

$5000

Find the best GPU for Nemotron 3.5 Lightning 30B-A3B

Build Hardware for Nemotron 3.5 Lightning 30B-A3B

QUANT	BPW	VRAM	QUALITY
IQ3_XXS	3.25	13.3 GB	82%
IQ3_XS	3.5	14.3 GB	84%
Q3_K_S	3.64	14.9 GB	85%
IQ3_M	3.76	15.3 GB	86%
Q3_K_M	4	16.3 GB	88%
Q3_K_L	4.3	17.5 GB	90%
IQ4_XS	4.46	18.1 GB	92%
Q4_K_S	4.67	18.9 GB	93%
Q4_K_M	4.89	19.8 GB	94%
Q5_K_S	5.57	22.5 GB	96%
Q5_K_M	5.7	23.0 GB	96%
Q6_K	6.56	26.4 GB	97%
Q8_0	8.5	34.0 GB	100%
FP16	16	63.6 GB	100%

Nemotron 3.5 Lightning 30B-A3B

Quantization Options

Community Ratings

Benchmarks (6)

Run this model

Auto-setup with fitmyllm CLI

GPUs that can run this model

Nemotron 3.5 Lightning 30B-A3B — 31.58B MoE.