Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

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

communityMoE

On disk17.4 GB

Memoryabout 21 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 mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

OptiQ Code

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

optiq serve --model mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits
optiq code

OptiQ Lab

optiq lab --model mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

Claude Code

optiq run claude -m mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

Codex

optiq run codex -m mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

OpenCode

optiq run opencode -m mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

Mistral Vibe

optiq run vibe -m mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

Hermes Agent

optiq run hermes -m mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

OpenClaw

optiq run openclaw -m mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits

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/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits")
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	17.4 GB
Memory needed	about 21 GB
Images	no, text only
Downloads	27 in the last month
Updated	2026-06-19
Hugging Face	mlx-community/Nex-N2-mini-mlx-optiq-static-mixed-3_6bits