FitGPU PickerBenchmarks PricesMethodology Submit resultsAbout SponsorRoadmap

← All benchmarks

llama3.1:8b on AMD Radeon 890M integrated GPU

Measured by FitGPU

AMD Radeon 890M integrated GPU · llama3.1:8b: 14.0 gen tok/s

GPUAMD Radeon 890M integrated GPU
CPUAMD Ryzen AI 9 HX 470
Modelllama3.1:8b (8.0B)
QuantQ4_K_M
Gen tok/s14.0 (median of 3 runs)
Prompt tok/s582
Context / predict4096 / 256
RuntimeOllama
Date2026-10-17

Compare all results

Measured with Ollama (median of 3 runs, 4K context, 256 generated tokens). See methodology.