---
title: "Frequently asked questions"
description: "Short answers to common installation, model, backend, API, and speculative-decoding questions."
canonical: "https://www.fermionresearch.com/docs/faq/"
source: "Fermion Research"
---

Docs / Integrity and support

# Frequently asked questions

Short answers to common installation, model, backend, API, and speculative-decoding questions.

## Common questions

Why is the package fermion-research but the command fermion?

Where do model files go?

Why is my machine slower than the published rate?

Is temperature zero deterministic?

Why does chat sample while generate does not?

Can I use the OpenAI SDK?

Why did a tool name change in the response?

What is fermion_stuck?

Does speculative decoding change the answer?

Can I use Transformers, llama.cpp, or MLX?

Why does Transformers reject the Hub id?

How do I know a download is complete?

Is the server safe to expose publicly?

Why do seed, JSON mode, or presence penalty not work?

## Still stuck?

Source: [https://www.fermionresearch.com/docs/faq/](https://www.fermionresearch.com/docs/faq/)