§ 004 / MEASURED FIT RECEIPT

RTX 5090 32GB runs Llama 3.1 8B.

One reproducible answer from owned hardware. The number below is tied to the exact quant, context, workload, and runtime setup shown.

Try this on my rig Preview receipt card Open receipt markdown

GPU

RTX 5090 32GB

Model tag

llama3.1:8b

Generation

228.9 tok/s

Measured

2026-07-09

measured on real hardware

Headline run

Q4_K_M · 4K context

Workload

Short generation · 256 tokens

Prompt eval

679 tok/s

Peak VRAM

7.2 GB

Source date

2026-07-09

Run command

ollama run llama3.1:8b

All recorded runs

Context changes the memory budget and speed. A result measured at 4K is not a measured claim at 8K.

Measured runs for RTX 5090 32GB and Llama 3.1 8B
Context	Workload	Quant	Generation	Prompt	Peak VRAM
4K context	Short generation · 256 tokens	Q4_K_M	228.9 tok/s	679	7.2 GB
4K context	Agent code task · 512 tokens	Q4_K_M	227.8 tok/s	1,028	7.8 GB
8K context	Long-context summarize	Q4_K_M	206.7 tok/s	12,109	7.8 GB

Evidence and next step

This receipt is a measured data point, not a promise that every runtime or driver behaves identically. The source record is kept below so the claim can be audited and extended with the next run.

Reports/5090/benchmarks/2026-07-09-5090-sweep-llama8b-gemma26b.csv via /5090-reports/latest.md

Enter your GPU and save your rig for future model drops →