local.ailocal.aiEarly access
HardwareModelsEnergyWallReferralsContact
HardwareModelsEnergyWallReferralsContactClaim your nameAccount

Search

Find people, models, hardware, or pages

Account
Model

Gpt Oss 20B

Intelligence rank
#87/216
43
Speed rank
#10/216
33s
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.

best37404313.8GBDisk Size (lower →)Intelligence (higher →)mxfp4 · 43% intelligence · 13.8GB disk sizemxfp4mxfp4 · Dflash · k=7 · 37% intelligence · 13.8GB disk sizemxfp4 · Dflash · k=7
Intelligence Density

Intelligence ÷ Disk Size (GB).

  1. 3.14
    mxfp4
  2. 2.67
    mxfp4 · Dflash · k=7
Hardware

Cost / task speed

Hardware cost / task speed
2 of 2 variations

Model variations

·
3643
Any intelligence
best33s1m 23s3m 32s$13.0k$6.7k$3.5kHardware cost (lower →)Task time (faster →)mxfp4 (43) · NVIDIA DGX Spark 128GB · vllm · $4.7k · 3m 14sSparkmxfp4 (43) · NVIDIA GeForce RTX 4090 24GB · vllm · $3.5k · 48sRTX 4090mxfp4 (43) · NVIDIA GeForce RTX 5090 32GB · vllm · $3.7k · 33sRTX 5090mxfp4 (43) · NVIDIA RTX 6000 Ada 48GB · vllm · $9.0k · 51sRTX6k Adamxfp4 (43) · NVIDIA RTX PRO 6000 Blackwell 96GB · vllm · $13.0k · 34sRTXPro6kmxfp4 (43)mxfp4 · Dflash · k=7 (37) · NVIDIA DGX Spark 128GB · vllm · $4.7k · 3m 32sSparkmxfp4 · Dflash · k=7 (37)

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