---
schema_version: '1.0'
id: news-20260826-b9b006
title: MacでLLMを動かすときMLX版はGGUF版に比べてプロンプト処理がかなり遅い - きしだのHatena
url: https://nowokay.hatenablog.com/entry/2025/12/28/225151
url_hash: b9b0066c9df2694ac099e80897da0bea33372523a1db8b3a43ca320fcbb17923
canonical_url: https://nowokay.hatenablog.com/entry/2025/12/28/225151
source: nowokay.hatenablog.com
category: news/tech
category_raw: it_ai
region: null
tags:
- it
- it_ai
- claude
- web-research
lang: null
published_at: '2025-12-28T13:51:51Z'
fetched_at: '2026-08-26T17:02:07.812279Z'
updated_at: '2026-08-26T17:06:19Z'
status: published
content_hash: null
content_changed_at: null
license_note: link-only
summary: null
summary_source: null
summary_en: null
summary_omitted_reason: license_restricted
redistribution: false
keywords_en:
- artificial intelligence
- Claude
- GGUF
- Hatena
- it
- it_ai
- LLM
- Mac
- MLX
- technology
- web-research
entities_en:
- name: Claude
  type: artifact
- name: LLM
  type: concept
- name: Mac
  type: device
topics_en:
- artificial intelligence
- technology
numeric_facts: []
entities:
- name: Claude
  type: artifact
- name: Mac
  type: device
- name: LLM
  type: concept
key_facts: []
related: []
related_auto:
- name: FileVault
  type: concept
  weight: 1.0
- name: Tailscale
  type: organization
  weight: 1.0
- name: 自宅サーバー
  type: artifact
  weight: 1.0
- name: RTX_4060
  type: artifact
  weight: 1.0
- name: スポーツ戦術AI
  type: concept
  weight: 1.0
computed_at: '2026-08-26T17:06:15Z'
---

# MacでLLMを動かすときMLX版はGGUF版に比べてプロンプト処理がかなり遅い - きしだのHatena

## TL;DR
（要約なし・原文はリンク先を参照 / No summary available; see the source link.）

## Key Points
- it / it_ai / claude / web-research

## Details
(本文なし。リンク先参照)

## Source
元記事: [MacでLLMを動かすときMLX版はGGUF版に比べてプロンプト処理がかなり遅い - きしだのHatena](https://nowokay.hatenablog.com/entry/2025/12/28/225151) — published 2025-12-28T13:51:51Z