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

SmolVLM2-500M-Video-Instruct-mlx

from HuggingFaceTB/SmolLM2-360M-Instruct
Video + text · Hugging Face ↓ 5.3K · ♥ 18
Params
507M
Weights
≈ 1.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-20

SmolVLM2-256M-Video-Instruct-mlx

from HuggingFaceTB/SmolLM2-360M-Instruct
Video + text · Hugging Face ↓ 717 · ♥ 10
Params
256M
Weights
≈ 513 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-26

Molmo2-8B-4bit

from Qwen/Qwen3-8B
4-bit
Video + text · Qwen ↓ 201 · ♥ 2
Params
8.7B
Weights
≈ 6.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-01-11

Molmo2-8B-8bit

from Qwen/Qwen3-8B
8-bit
Video + text · Qwen ↓ 86 · ♥ 0
Params
8.7B
Weights
≈ 10.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-01-11

Molmo2-8B-6bit

from Qwen/Qwen3-8B
6-bit
Video + text · Qwen ↓ 46 · ♥ 0
Params
8.7B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-01-11

Molmo2-8B-5bit

from Qwen/Qwen3-8B
5-bit
Video + text · Qwen ↓ 41 · ♥ 0
Params
8.7B
Weights
≈ 7.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-01-11

Molmo2-8B-fp16

from Qwen/Qwen3-8B
fp16
Video + text · Qwen ↓ 41 · ♥ 0
Params
8.7B
Weights
≈ 17.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-01-11