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

4 builds · clear filters

Qwen3-Embedding-8B-mxfp8

from Qwen/Qwen3-8B-Base

MXFP8

Embeddings · Qwen ↓ 1.0K · ♥ 4

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-02-11

CLM-v0.1-8B-MLX-8bit

from Qwen/Qwen3-8B

8-bit

Embeddings · Qwen ↓ 635 · ♥ 9

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-09-29

CLM-v0.1-8B-MLX-4bit

from Qwen/Qwen3-8B

4-bit

Embeddings · Qwen ↓ 104 · ♥ 1

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-09-29

CLM-v0.1-8B-MLX-5bit

from Qwen/Qwen3-8B

5-bit

Embeddings · Qwen ↓ 46 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-09-29