mxbai-rerank-large-v2-OptiQ-4bit

mixedbread-ai/mxbai-rerank-large-v2, quantized with OptiQ by nisavid for Apple Silicon.

community

On disk1.2 GB

Memoryabout 3 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 nisavid/mxbai-rerank-large-v2-OptiQ-4bit

OptiQ Code

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

optiq serve --model nisavid/mxbai-rerank-large-v2-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model nisavid/mxbai-rerank-large-v2-OptiQ-4bit

Claude Code

optiq run claude -m nisavid/mxbai-rerank-large-v2-OptiQ-4bit

Codex

optiq run codex -m nisavid/mxbai-rerank-large-v2-OptiQ-4bit

OpenCode

optiq run opencode -m nisavid/mxbai-rerank-large-v2-OptiQ-4bit

Mistral Vibe

optiq run vibe -m nisavid/mxbai-rerank-large-v2-OptiQ-4bit

Hermes Agent

optiq run hermes -m nisavid/mxbai-rerank-large-v2-OptiQ-4bit

OpenClaw

optiq run openclaw -m nisavid/mxbai-rerank-large-v2-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("nisavid/mxbai-rerank-large-v2-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Qwen · Qwen docs
Architecture	Qwen2
Base model	mixedbread-ai/mxbai-rerank-large-v2
Size on disk	1.2 GB
Memory needed	about 3 GB
Images	no, text only
Downloads	25 in the last month
Updated	2026-07-12
Hugging Face	nisavid/mxbai-rerank-large-v2-OptiQ-4bit