Nemotron-3 MLX (Apple Silicon) - a pipenetwork Collection

pipenetwork 's Collections

Qwen3.8-2.4T-A95B MLX (REAP)

Muse-Glimmer 30B MLX

Inkling-Small · MLX

DeepSeek-V4-Flash · MLX

Nemotron TwoTower · MLX

Qwen3.6-35B-A3B — MLX

Ornith-1.0-397B — MLX

GLM-5.2 REAP (expert-pruned)

Rio-3.1-Open-30B MLX

Gemma-4-26B-A4B-it MLX

Gemma-4-31B-it MLX

Kimi-K2.7-Code MLX

Holo-3.1 MLX (computer-use)

Frog (SWE/debugging) MLX

Nemotron-3 MLX (Apple Silicon)

Nemotron-3 MLX (Apple Silicon)

updated Jul 15

MLX quants of NVIDIA Nemotron-3 for Apple Silicon: Ultra 550B (4/5/6/8-bit) and dense Nano-4B (4/8-bit), converted with mlx-lm.

pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-4bit

Text Generation • 549B • Updated Jun 5 • 120

Note Ultra 550B 4-bit (~288GB) - recommended, single 512GB M3 Ultra
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-8bit

Text Generation • 549B • Updated Jun 5 • 78

Note Ultra 550B 8-bit (~584GB) - multi-Mac shard
pipenetwork/NVIDIA-Nemotron-3-Nano-4B-MLX-8bit

1B • Updated Jun 5 • 4

Note Nano 4B 8-bit (~4GB) - near-lossless, 16GB+ Macs
pipenetwork/NVIDIA-Nemotron-3-Nano-4B-MLX-4bit

0.6B • Updated Jun 5 • 2

Note Nano 4B 4-bit (~2GB) - smallest