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

78 builds · page 2 of 2 · clear filters

AceReason-Nemotron-7B-bf16

from nvidia/AceReason-Nemotron-7B
bf16
Text generation · NVIDIA ↓ 43 · ♥ 0
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

nvidia-open-model-license · updated 2025-05-26

AceReason-Nemotron-1.1-7B-8bit

from nvidia/AceReason-Nemotron-1.1-7B
8-bit
Text generation · NVIDIA ↓ 42 · ♥ 0
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

nvidia-open-model-license · updated 2025-06-17

AceReason-Nemotron-14B-bf16

from nvidia/AceReason-Nemotron-14B
bf16
Text generation · NVIDIA ↓ 42 · ♥ 0
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+

nvidia-open-model-license · updated 2025-05-24

Nemotron-Cascade-2-30B-A3B-5bit

from nvidia/Nemotron-Cascade-2-30B-A3B
5-bit
Text generation · NVIDIA ↓ 41 · ♥ 1
Params
32B
Weights
≈ 21.7 GB
Mac memory
32 GB+

nvidia-open-model-license · updated 2026-03-20

Nemotron-Cascade-2-30B-A3B-mxfp4

from nvidia/Nemotron-Cascade-2-30B-A3B
MXFP4
Text generation · NVIDIA ↓ 39 · ♥ 1
Params
32B
Weights
≈ 17.8 GB
Mac memory
24 GB+

nvidia-open-model-license · updated 2026-04-30

Llama-3_3-Nemotron-Super-49B-v1-mlx-6bit

from nvidia/Llama-3_3-Nemotron-Super-49B-v1
6-bit
Text generation · NVIDIA ↓ 39 · ♥ 0
Params
50B
Weights
≈ 40.5 GB
Mac memory
48 GB+

nvidia-open-model-license · updated 2025-04-08

Nemotron-Cascade-2-30B-A3B-bf16

from nvidia/Nemotron-Cascade-2-30B-A3B
bf16
Text generation · NVIDIA ↓ 37 · ♥ 0
Params
32B
Weights
≈ 63.2 GB
Mac memory
96 GB+

nvidia-open-model-license · updated 2026-04-30

Orchestrator-8B-6bit

from nvidia/Nemotron-Orchestrator-8B
6-bit
Text generation · NVIDIA ↓ 33 · ♥ 1
Params
8.2B
Weights
≈ 6.7 GB
Mac memory
16 GB+

updated 2025-11-29

OpenMath-Nemotron-32B-4bit

from nvidia/OpenMath-Nemotron-32B
4-bit
Text generation · NVIDIA ↓ 33 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

cc-by-4.0 · updated 2025-04-27

OpenMath-Nemotron-7B-4bit

from nvidia/OpenMath-Nemotron-7B
4-bit
Text generation · NVIDIA ↓ 33 · ♥ 0
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

cc-by-4.0 · updated 2025-04-24

OpenReasoning-Nemotron-32B-4bit

from nvidia/OpenReasoning-Nemotron-32B
4-bit
Text generation · NVIDIA ↓ 32 · ♥ 0
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

cc-by-4.0 · updated 2025-07-22

OpenMath-Nemotron-14B-4bit

from nvidia/OpenMath-Nemotron-14B
4-bit
Text generation · NVIDIA ↓ 31 · ♥ 0
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

cc-by-4.0 · updated 2025-04-25

OpenMath-Nemotron-1.5B-4bit

from nvidia/OpenMath-Nemotron-1.5B
4-bit
Text generation · NVIDIA ↓ 29 · ♥ 0
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+

cc-by-4.0 · updated 2025-04-24

Orchestrator-8B-5bit

from nvidia/Nemotron-Orchestrator-8B
5-bit
Text generation · NVIDIA ↓ 29 · ♥ 0
Params
8.2B
Weights
≈ 5.6 GB
Mac memory
16 GB+

updated 2025-11-29

Nemotron-Cascade-2-30B-A3B-mxfp8

from nvidia/Nemotron-Cascade-2-30B-A3B
MXFP8
Text generation · NVIDIA ↓ 28 · ♥ 0
Params
32B
Weights
≈ 33.6 GB
Mac memory
48 GB+

nvidia-open-model-license · updated 2026-04-30

Orchestrator-8B-bf16

from nvidia/Nemotron-Orchestrator-8B
bf16
Text generation · NVIDIA ↓ 24 · ♥ 1
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+

updated 2025-11-29

Nemotron-3-Ultra-550B-A55B-bf16

from nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
bf16
Text generation · NVIDIA ↓ 0 · ♥ 0
Params
—
Weights
—
Mac memory
—

nvidia-open-model-license · updated 2026-06-04