Home / Skills / convert-quantize
convert-quantize
Blaizzy/mlx-vlmSkill
Use this skill when the user wants to convert a Hugging Face model to MLX or quantize/dequantize one with mlx_vlm.convert, including bits and group size, quant modes (affine, mxfp4, nvfp4, mxfp8), RTN vs AWQ, mixed-bit recipes, dtype casts, calibration (text or multimodal), local vs Hub paths, revisions, uploading to the Hub, and convert/quant errors.
Why this score
This repo hosts 8 skills, so its 5,640 stars are split between them (about 705 each) for scoring.
Popularity score: 79/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit 9527f2da3b42, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneconvert-quantize Blaizzy/mlx-vlm · Skill | 79 | ★ 5.6k | ≈93 always | 16d ago |
| convert-web-app modelcontextprotocol/ext-apps · Skill Both about convert | 64 | ★ 3.0k | ≈131 always | 1mo ago |
| convert remotion-dev/remotion · Skill Both about convert and local | 79 | ★ 65k | ≈54 always | 16d ago |
| data-convert dathere/qsv · Skill Both about convert | 63 | ★ 3.8k | ≈22 always | 16d ago |
| jaspr-convert-html rodydavis/signals.dart · Skill Both about convert | 62 | ★ 821 | ≈27 always | 2mo ago |
| shinka-convert SakanaAI/ShinkaEvolve · Skill Both about convert | 71 | ★ 1.5k | ≈92 always | 1mo ago |