local.ailocal.aiEarly access
HardwareModelsEnergyWallReferralsContact
HardwareModelsEnergyWallReferralsContactClaim your nameAccount

Search

Find people, models, hardware, or pages

Account
Model

Nemotron 3 Nano 30B A3B

Intelligence rank
#88/216
42
Speed rank
#9/216
30s
Fastest hardware: NVIDIA GeForce RTX 5090 32GB.

Quick Start

Variations

Intelligence / Disk Size

Variations

Verified model-weight disk size. Higher intelligence and lower disk size are better.

best41424232.7GB26.0GB19.3GBDisk Size (lower →)Intelligence (higher →)nvfp4 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 · 41% intelligence · 19.3GB disk sizenvfp4 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4fp8 · 42% intelligence · 32.7GB disk sizefp8
Intelligence Density

Intelligence ÷ Disk Size (GB).

  1. 2.12
    nvfp4 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4
  2. 1.30
    fp8
Hardware

Cost / task speed

Hardware cost / task speed
2 of 2 variations

Model variations

·
4042
Any intelligence
best30s1m 33s4m 49s$13.0k$7.0k$3.7kHardware cost (lower →)Task time (faster →)nvfp4 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 (41) · NVIDIA DGX Spark 128GB · vllm · $4.7k · 3m 17sSparknvfp4 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 (41) · NVIDIA GeForce RTX 5090 32GB · vllm · $3.7k · 30sRTX 5090nvfp4 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 (41) · NVIDIA RTX 6000 Ada 48GB · vllm · $9.0k · 57sRTX6k Adanvfp4 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 (41)fp8 (42) · NVIDIA DGX Spark 128GB · vllm · $4.7k · 4m 49sSparkfp8 (42) · NVIDIA RTX 6000 Ada 48GB · vllm · $9.0k · 1m 10sRTX6k Adafp8 (42) · NVIDIA RTX PRO 6000 Blackwell 96GB · vllm · $13.0k · 51sRTXPro6kfp8 (42)

Each coloured line is that variation’s cost / task-speed Pareto frontier. Global is the frontier across every qualifying variation; every point is still one original measured configuration.

Frontier →the ranked leaderboardAll models →every measured modelHardware →every measured device
local.aiIndependent local-AI benchmarks
AboutReferralsAccountContact
Live benchmark data