Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 53m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

Search Fits in Task Vendor Quantisation Sort

7 builds · clear filters

Qwen-Image-2512-4bit

from Qwen/Qwen-Image-2512

4-bit

Text to image · Qwen ↓ 16K · ♥ 9

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-01-01

Qwen-Image-2.1-mflux-q4

from Qwen/Qwen-Image-2.1

4-bit

Text to image · Qwen ↓ 11K · ♥ 2

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-09-26

Qwen-Image-2512-8bit

from Qwen/Qwen-Image

8-bit

Text to image · Qwen ↓ 5.2K · ♥ 4

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-01-01

Qwen-Image-2512-6bit

from Qwen/Qwen-Image-2512

6-bit

Text to image · Qwen ↓ 1.2K · ♥ 6

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-01-01

Qwen-Image-2512-3bit

from Qwen/Qwen-Image-2512

3-bit

Text to image · Qwen ↓ 566 · ♥ 3

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-01-01

Qwen-Image-2512-5bit

from Qwen/Qwen-Image-2512

5-bit

Text to image · Qwen ↓ 386 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-01-01

Qwen-Image-2.1-MLX-4bit

from Qwen/Qwen-Image-2.1

4-bit

Text to image · Qwen ↓ 0 · ♥ 19

Params

—

Weights

—

Mac memory

—

qwen-research · updated 2026-09-20