mlx-optiq
← Models

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16, quantized by OptiQ for Apple Silicon; mixture-of-experts.

MoEMTP head
On disk22.8 GB
Memoryabout 27 GB
Capability Score73.94

Capability Score breakdown

The six metrics behind this model's Capability Score of 73.94, as reported in the model card.

Capability Score breakdown: NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bitMMLU: This model 78.9; GSM8K: This model 85.5; IFEval: This model 68.4; BFCL-V3: This model 83.0; HumanEval: This model 87.8; HashHop: This model 40.0MMLU78.9GSM8K85.5IFEval68.4BFCL-V383.0HumanEval87.8HashHop40.0

Use it

Install

pip install mlx-optiq

Serve it

An OpenAI- and Anthropic-compatible server on this Mac. Every app below can use it.

optiq serve --model mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

OptiQ Code

The terminal coding agent uses whatever model optiq serve is running.

optiq serve --model mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

Claude Code

optiq run claude -m mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

Codex

optiq run codex -m mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

OpenCode

optiq run opencode -m mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

Mistral Vibe

optiq run vibe -m mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

Hermes Agent

optiq run hermes -m mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

OpenClaw

optiq run openclaw -m mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit

optiq run starts optiq serve if it is not running, sets the agent up for this session only, and stops the server when the agent exits.

mlx-lm, text only

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

FamilyNemotron · Nemotron docs
ArchitectureNemotron-H
Base modelnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Size on disk22.8 GB
Memory neededabout 27 GB
Imagesno, text only
MTP headincluded
Capability Score73.94 (from the model card)
Downloads1,063 in the last month
Updated2026-09-15
Hugging Facemlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bit