Nex-N2-mini-mlx-OptiQ-4bit

nex-agi/Nex-N2-mini, quantized with OptiQ by jedisct1 for Apple Silicon; mixture-of-experts.

communityMoE

On disk20.4 GB

Memoryabout 25 GB

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 jedisct1/Nex-N2-mini-mlx-OptiQ-4bit

OptiQ Code

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

optiq serve --model jedisct1/Nex-N2-mini-mlx-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model jedisct1/Nex-N2-mini-mlx-OptiQ-4bit

Claude Code

optiq run claude -m jedisct1/Nex-N2-mini-mlx-OptiQ-4bit

Codex

optiq run codex -m jedisct1/Nex-N2-mini-mlx-OptiQ-4bit

OpenCode

optiq run opencode -m jedisct1/Nex-N2-mini-mlx-OptiQ-4bit

Mistral Vibe

optiq run vibe -m jedisct1/Nex-N2-mini-mlx-OptiQ-4bit

Hermes Agent

optiq run hermes -m jedisct1/Nex-N2-mini-mlx-OptiQ-4bit

OpenClaw

optiq run openclaw -m jedisct1/Nex-N2-mini-mlx-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("jedisct1/Nex-N2-mini-mlx-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Qwen · Qwen docs
Architecture	Qwen3.5 MoE
Base model	nex-agi/Nex-N2-mini
Size on disk	20.4 GB
Memory needed	about 25 GB
Images	no, text only
Downloads	20 in the last month
Updated	2026-06-10
Hugging Face	jedisct1/Nex-N2-mini-mlx-OptiQ-4bit