<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Model Conversion on 每日拍拍</title>
    <link>https://dailypypy.org/tags/model-conversion/</link>
    <description>Recent content in Model Conversion on 每日拍拍</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-tw</language>
    <copyright>© 2026 每日拍拍</copyright>
    <lastBuildDate>Tue, 25 Aug 2026 10:44:00 +0800</lastBuildDate><atom:link href="https://dailypypy.org/tags/model-conversion/index.xml" rel="self" type="application/rss+xml" />
    <follow_challenge>
      <feedId>155076163427069952</feedId>
      <userId>154825760438254592</userId>
    </follow_challenge>
    
    
    <item>
      <title>MLX-LM 模型轉換與量化：4/8-bit、Mixed Quant 與品質評測</title>
      <link>https://dailypypy.org/learn/mlx-lm-quantization-convert/</link>
      <pubDate>Tue, 25 Aug 2026 10:44:00 +0800</pubDate>
      
      <guid>https://dailypypy.org/learn/mlx-lm-quantization-convert/</guid>
      <description>&lt;!---
1440x768
prompt: masterpiece, best quality, highres, clean anime illustration, japanese anime style, soft shading, flat color design, 1girl, black hair, green eyes, white off-shoulder shirt, black short skirt, dutch angle, cowboy shot, leaning sideways while balancing two blank translucent geometric model blocks on open palms, playful analytical raised eyebrow and confident half-smile, looking at viewer, pastel dusty rose background, subtle floating layered chip shapes and tiny comparison dots without symbols or text, neat composition, detailed eyes, cute and smart vibe, minimal background, polished illustration, no text
negative prompt: worst quality, bad eye, bad hand, extra limbs, manga, multiple views, monochrome, text, signature
dedup note: This is a quantization-specific follow-up to ../python-mlx/ and ../mlx-lm-local-models/. The older MLX overview shows one basic 4-bit conversion command, while the MLX-LM inference post only recommends pre-quantized models. This article focuses on reproducible Hugging Face-to-MLX conversion, 4/8-bit and group-size trade-offs, built-in mixed-bit recipes, artifact validation, and an A/B evaluation harness for size, peak memory, speed, and task quality. It does not repeat general MLX arrays, model selection, chat templates, streaming, server, batch-runner, embeddings, or LoRA workflows.
---&gt;
&lt;p&gt;





&lt;figure&gt;
    &lt;img class=&#34;my-0 rounded-md&#34; loading=&#34;lazy&#34; alt=&#34;featured&#34; src=&#34;./featured.png&#34; /&gt;

  
&lt;/figure&gt;
&lt;/p&gt;</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://dailypypy.org/learn/mlx-lm-quantization-convert/featured.png" />
    </item>
    
  </channel>
</rss>
