Instructions to use dealignai/LFM2.5-8B-A1B-MXFP8-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/LFM2.5-8B-A1B-MXFP8-CRACK with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("dealignai/LFM2.5-8B-A1B-MXFP8-CRACK")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use dealignai/LFM2.5-8B-A1B-MXFP8-CRACK with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dealignai/LFM2.5-8B-A1B-MXFP8-CRACK with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default dealignai/LFM2.5-8B-A1B-MXFP8-CRACK

Run Hermes

hermes

OpenClaw new

How to use dealignai/LFM2.5-8B-A1B-MXFP8-CRACK with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use dealignai/LFM2.5-8B-A1B-MXFP8-CRACK with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Built for vMLX — the MLX inferencer with KV-cache quantization, prefix-cache reuse, agentic tool calling, and hybrid Conv1d+attention cache support.
_{Free for macOS · vmlx.net}

LFM 2.5 8B-A1B — MXFP8 CRACK

CRACK abliterated · 8-bit microscaling · Hybrid Conv1d + Attention + 32-expert MoE · Reasoning · 8.2 GB

What Is This?

This is LFM 2.5 8B-A1B by Liquid AI — a hybrid Conv1d + full-attention + 32-expert MoE (24 layers, 8B total / ~1B active, 128k context, reasoning with <think> traces) that has been:

CRACK abliterated — refusal behavior removed at the weight level. The model now complies across all task categories instead of refusing, while keeping its knowledge, reasoning, and tool use intact.
8-bit microscaling quantized for MLX on Apple Silicon — 8.2 GB.

Results

Evaluated through the Osaurus runtime. Compliance graded via HarmBench-text refusal classifier; MMLU via logit-mode argmax over A/B/C/D token logits (matched on both base and CRACK with identical chat-template rendering).

HarmBench compliance (70 prompts · 10 per category)

Category	CRACK ASR
Chemical / biological	10 / 10 (100%)
Copyright	10 / 10 (100%)
Cybercrime / intrusion	10 / 10 (100%)
Harassment / bullying	10 / 10 (100%)
Illegal	10 / 10 (100%)
Misinformation / disinformation	10 / 10 (100%)
General harmful	10 / 10 (100%)
Overall	70 / 70 (100%)

MMLU-228 (57-subject, 4 q per subject)

Subject area	base	CRACK	Δ
Overall	52.6%	52.6%	+0.0pp
STEM	43.1%	40.3%	-2.8pp
Humanities	46.2%	51.9%	+5.7pp
Social Sciences	70.8%	66.7%	-4.1pp
Other (medicine, business, …)	55.4%	57.1%	+1.7pp

Features

128k context with hybrid cache
Reasoning — emits <think>...</think> traces; vMLX's reasoning parser surfaces them in message.reasoning_content and the final answer in message.content
Tool calling — Liquid Python-call syntax inside <|tool_call_start|>...<|tool_call_end|>, parsed by vMLX's lfm2 tool parser
Hybrid Conv1d + full-attention + 32-expert MoE (24 layers, ~1B active params)

Usage

Run with vMLX (recommended — supports hybrid cache + reasoning + tools) or an MLX runtime with lfm2_moe support.

Liquid AI recommends temperature=0.3, min_p=0.15, repetition_penalty=1.05 for general use.

# OpenAI-compatible chat completion
# POST /v1/chat/completions
{
  "model": "dealignai/LFM2.5-8B-A1B-MXFP8-CRACK",
  "messages": [{"role": "user", "content": "..."}],
  "temperature": 0.3, "min_p": 0.15,
  "repetition_penalty": 1.05
}

About CRACK

CRACK (Controlled Refusal Ablation via Calibrated Knockouts) removes safety-refusal behavior at the weight level so the model complies with all task categories while preserving reasoning quality, factual knowledge, and coherence.

Support dealignai

All models are built from original research and released free.

Support us on Ko-fi — membership gets early access and extras.

Ko-fi · X @dealignai · dealign.ai

See our research: Safety Generalization in Frontier Models

Disclaimer

This model has had its safety-refusal behavior removed for research purposes. It will follow instructions across all categories without refusing. You are solely responsible for how you use it and for complying with all applicable laws. Published for AI-safety research and authorized security testing.

Downloads last month: 198

Safetensors

Model size

8B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

8-bit

Model tree for dealignai/LFM2.5-8B-A1B-MXFP8-CRACK

Base model

LiquidAI/LFM2.5-8B-A1B-Base

Finetuned

LiquidAI/LFM2.5-8B-A1B

Quantized

(56)

this model