run a model
Running Llama 3.1 8B
The one every tutorial assumes. Old enough that every problem you hit has already been answered somewhere.
8 billion parametersweights ↗
memory needed
5.4 GB
the smallest hardware that runs it properly
the cheapest one you can actually buy today
the alternatives
on the processor alone: slow, and it works
on the processor alone: slow, and it works
on the processor alone: slow, and it works
if you change the format
- 4-bit weightswhat almost everyone runs, and what the hardware below is judged against
- 5.4 GB
- 8-bit weightsvisibly better on long or precise answers
- 9.8 GB
- 16-bit weightsthe model as it was trained, and rarely worth it at home
- 19.4 GB
Everything above assumes 4-bit weights and a 8k token context. Going up in precision costs memory; shortening the context is the other lever, and the cheaper one when something almost fits. Model details checked on 2026-08-02.
how to actually run it
what this page will not tell you
How many tokens per second you will get. That is a benchmark — it depends on memory bandwidth, on the engine, on the context and on how long the answers are. This site does not invent benchmarks, and everyone who quotes one for your exact setup is guessing.
builder
Price a whole machine around itA card is not a server. The builder adds the machine, the drives, the electricity and the backup.