← Models

LFM2.5-1.2B-Thinking-OptiQ-4bit

LiquidAI/LFM2.5-1.2B-Thinking, quantized by OptiQ for Apple Silicon.

On disk0.9 GB

Memoryabout 2 GB

Capability Score60.47

Capability Score breakdown

The six metrics behind this model's Capability Score of 60.47, as reported in the model card.

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/LFM2.5-1.2B-Thinking-OptiQ-4bit

OptiQ Code

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

optiq serve --model mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit
optiq code

OptiQ Lab

optiq lab --model mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit

Claude Code

optiq run claude -m mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit

Codex

optiq run codex -m mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit

OpenCode

optiq run opencode -m mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit

Mistral Vibe

optiq run vibe -m mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit

Hermes Agent

optiq run hermes -m mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit

OpenClaw

optiq run openclaw -m mlx-community/LFM2.5-1.2B-Thinking-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("mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Details

Family	LFM2.5 · LFM2.5 docs
Architecture	LFM2
Base model	LiquidAI/LFM2.5-1.2B-Thinking
Size on disk	0.9 GB
Memory needed	about 2 GB
Images	no, text only
Capability Score	60.47 (from the model card)
Downloads	270 in the last month
Updated	2026-10-14
Hugging Face	mlx-community/LFM2.5-1.2B-Thinking-OptiQ-4bit