MN-12B-Mag-Mell-R1-OptiQ-4bit

inflatebot/MN-12B-Mag-Mell-R1, quantized with OptiQ by jaithree for Apple Silicon.

community

On disk8.9 GB

Memoryabout 12 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 jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit

OptiQ Code

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

optiq serve --model jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit

Claude Code

optiq run claude -m jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit

Codex

optiq run codex -m jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit

OpenCode

optiq run opencode -m jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit

Mistral Vibe

optiq run vibe -m jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit

Hermes Agent

optiq run hermes -m jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit

OpenClaw

optiq run openclaw -m jaithree/MN-12B-Mag-Mell-R1-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("jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	Mistral · Devstral · Mistral · Devstral docs
Architecture	Mistral
Base model	inflatebot/MN-12B-Mag-Mell-R1
Size on disk	8.9 GB
Memory needed	about 12 GB
Images	no, text only
Downloads	88 in the last month
Updated	2026-07-26
Hugging Face	jaithree/MN-12B-Mag-Mell-R1-OptiQ-4bit