Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h 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

8 builds · clear filters

openai-privacy-filter-bf16

from openai/privacy-filter

bf16

Token classification · OpenAI · gpt-oss ↓ 420 · ♥ 3

Params

1.4B

Weights

≈ 2.8 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-23

openai-privacy-filter-4bit

from openai/privacy-filter

4-bit

Token classification · OpenAI · gpt-oss ↓ 413 · ♥ 6

Params

1.4B

Weights

≈ 790 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-23

openai-privacy-filter-8bit

from openai/privacy-filter

8-bit

Token classification · OpenAI · gpt-oss ↓ 267 · ♥ 2

Params

1.4B

Weights

≈ 1.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-23

openai-privacy-filter-mxfp8

from openai/privacy-filter

MXFP8

Token classification · OpenAI · gpt-oss ↓ 219 · ♥ 1

Params

1.4B

Weights

≈ 1.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-23

openai-privacy-filter-nvfp4

from openai/privacy-filter

Token classification · OpenAI · gpt-oss ↓ 190 · ♥ 1

Params

1.4B

Weights

≈ 5.6 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-04-23

openai-privacy-filter-mxfp4

from openai/privacy-filter

MXFP4

Token classification · OpenAI · gpt-oss ↓ 186 · ♥ 1

Params

1.4B

Weights

≈ 790 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-23

openai-privacy-filter-6bit

from openai/privacy-filter

6-bit

Token classification · OpenAI · gpt-oss ↓ 168 · ♥ 1

Params

1.4B

Weights

≈ 1.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-23

openai-privacy-filter-5bit

from openai/privacy-filter

5-bit

Token classification · OpenAI · gpt-oss ↓ 162 · ♥ 0

Params

1.4B

Weights

≈ 965 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-23