MemReranker-4B-OptiQ-4bit

IAAR-Shanghai/MemReranker-4B, quantized with OptiQ by nisavid for Apple Silicon.

community

On disk3.0 GB

Memoryabout 5 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/MemReranker-4B-OptiQ-4bit

OptiQ Code

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

optiq serve --model nisavid/MemReranker-4B-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model nisavid/MemReranker-4B-OptiQ-4bit

Claude Code

optiq run claude -m nisavid/MemReranker-4B-OptiQ-4bit

Codex

optiq run codex -m nisavid/MemReranker-4B-OptiQ-4bit

OpenCode

optiq run opencode -m nisavid/MemReranker-4B-OptiQ-4bit

Mistral Vibe

optiq run vibe -m nisavid/MemReranker-4B-OptiQ-4bit

Hermes Agent

optiq run hermes -m nisavid/MemReranker-4B-OptiQ-4bit

OpenClaw

optiq run openclaw -m nisavid/MemReranker-4B-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/MemReranker-4B-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Qwen · Qwen docs
Architecture	Qwen3
Base model	IAAR-Shanghai/MemReranker-4B
Size on disk	3.0 GB
Memory needed	about 5 GB
Images	no, text only
Downloads	30 in the last month
Updated	2026-07-11
Hugging Face	nisavid/MemReranker-4B-OptiQ-4bit