Qwen3.5 9B

Qwen (Alibaba)

Free

Get

MLX Score4.2

PriceFreeno paid plan

RunsOn your Mac

DeveloperQwen (Alibaba)

LicenceOpenApache-2.0

CategoryModels

Mac14.0+macOS or later

Qwen3.5 9B is a small dense vision-language model trained on text and images together. Qwen says it covers 201 languages and dialects, and it has a 262,144-token context, extensible to about 1 million.

A 4-bit MLX build is about 6 GB; on mlx.app's estimate it fits a Mac with 16 GB of memory.

Open weights under Apache 2.0. Run locally, nothing leaves your Mac.

How to Get It

Run it on your MacSee how

WebsiteVisit

Official downloads only. MLX never re-hosts an app, and never runs a command for you.

MLX Score

4.2out of 5

Hugging Face downloads and likesahead of 80%

Hugging Face: 6,412,961 downloads (30 days), 2,295 likes · read 2026-11-02

Ranked against the open models listings, from real public data only. How the score works.

Information

Developer: Qwen (Alibaba)
Category: Open models
Price: Free (Open weights, free to download.)
Your data: Runs on your Mac
Licence: Apache-2.0
Mac: macOS 14.0 or later
iPhone and iPad: —
Needs: 16 GB memory
Links: Website · Hugging Face
Facts checked: 2026-11-01

Sources

huggingface.co/Qwen/Qwen3.5-9B · Apache-2.0, 9B parameters, 201 languages, 262,144-token context (extensible to 1,010,000), image-text-to-text · checked 2026-11-01huggingface.co/mlx-community/Qwen3.5-9B-MLX-4bit · 4-bit MLX build (about 6 GB) · checked 2026-11-01ml-explore.github.io/mlx/build/html/install.html · macOS 14.0 minimum (MLX needs Apple silicon and macOS 14.0+) · checked 2026-11-01mlx.app/run/qwen3.5-9b · memory: smallest Mac (16 GB) where the 4-bit MLX build fits with room for context, from lib/compare (75% of unified memory usable) · checked 2026-11-01Icon from Hugging Face

See All