Hardware Benchmarks

Best Local LLM Performance for RTX 5080

Compare RTX 5080 benchmark results and see which models actually earn the best completed quality scores.

Hardware Overview

GPU-specific specifications for local LLM planning.

NVIDIA GeForce RTX 5080
VRAM
15GB

Recommended Models

Models we recommend for RTX 5080.

Fastest benchmarked model

gpt-oss:20b

20.9B

64.0 tok/s

This benchmark delivered the highest token generation speed at 64.0 tok/s.

Best-quality benchmarked model

qwen3.5:9b

9.7B

24.1 tok/sQuality 66.4

This benchmark has the highest completed quality score at 66.4.

Benchmark Results

Completed quality-ranked benchmark results for NVIDIA GeForce RTX 5080.