Skip to content
AI Model Radar
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

8 builds · clear filters

VL-Rethinker-72B-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Visual question answering · Qwen ↓ 24 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-16

VL-Rethinker-7B-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Visual question answering · Qwen ↓ 20 · ♥ 0
Params
8.3B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-16

VL-Rethinker-7B-6bit

from Qwen/Qwen2.5-VL-7B-Instruct
6-bit
Visual question answering · Qwen ↓ 19 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-16

VL-Rethinker-7B-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Visual question answering · Qwen ↓ 18 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-16

VL-Rethinker-7B-fp16

from Qwen/Qwen2.5-VL-7B-Instruct
fp16
Visual question answering · Qwen ↓ 18 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-04-16

VL-Rethinker-72B-fp16

from Qwen/Qwen2.5-VL-7B-Instruct
fp16
Visual question answering · Qwen ↓ 16 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-16

VL-Rethinker-72B-6bit

from Qwen/Qwen2.5-VL-7B-Instruct
6-bit
Visual question answering · Qwen ↓ 15 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-16

VL-Rethinker-72B-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Visual question answering · Qwen ↓ 15 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-16