Instructions to use dealignai/Laguna-S-2.1-JANG_6M-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-CRACK"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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/Laguna-S-2.1-JANG_6M-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use dealignai/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-CRACK"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "dealignai/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-CRACK",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use dealignai/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-CRACK

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dealignai/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-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/Laguna-S-2.1-JANG_6M-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"

Built for vMLX — the MLX inferencer with KV-cache quantization, prefix-cache reuse, agentic tool calling, and mixed-precision JANG bundles.
_{Free for macOS · vmlx.net}

⚡ All JANG models are meant to be run in vMLX

Laguna S-2.1 — JANG_6M CRACK

CRACK abliterated · JANG mixed-precision (MLX affine) · Agentic coding · Reasoning toggle · Tool calling · 262K context · ~90 GB

What Is This?

This is poolside/Laguna-S-2.1 — a 118B-parameter Mixture-of-Experts model (48 layers, 256 routed experts top-10 + shared expert, hybrid global + sliding-window attention, 262K context) built for agentic coding — that has been:

CRACK abliterated — refusal behavior removed at the weight level, so it complies across task categories instead of refusing, while keeping its coding ability, knowledge, and reasoning intact.
JANG_6M quantized — the highest-precision mixed-precision affine MLX bundle for Apple Silicon (~90 GB). High-precision attention, shared expert, router, and norms; the routed-expert bulk carries the higher-bit weight.

Text-only. Reasoning and tool calling fully preserved.

Results

Evaluated through the vMLX inference engine. HarmBench scored with a strict classifier (rejects loops, empty/template dumps, and thinking-trace leakage). MMLU is the standard 57-subject multiple-choice benchmark in logit mode.

Metric	Base	CRACK
MMLU (57-subject)	76.1%	75.9% (−0.23)
HarmBench-320 (compliance / ASR)	—	99.7% (319/320)

Abliteration is capability-neutral — MMLU moves −0.23 points, within run-to-run noise, while removing refusals. The model stays coherent in both direct and reasoning modes.

MMLU by topic (base vs CRACK)

Category	Base	CRACK	Δ
STEM	72.1%	72.3%	+0.2
Humanities	76.4%	75.9%	−0.5
Social Sciences	81.7%	81.9%	+0.3
Other	76.7%	75.6%	−1.0
Overall (57 subj)	76.1%	75.9%	−0.23

HarmBench by category

Category	Compliance
Standard	(see 319/320 overall — near-perfect)
Overall	99.7% (319/320)

Features

Agentic coding — Laguna-S's core strength, preserved through abliteration + quantization.
Reasoning toggle — enable_thinking=True (default, full chain-of-thought) or enable_thinking=False (direct answers). DeepSeek-R1-style think tags.
Tool calling — native <tool_call> schema preserved.
262K context · text-only.

Usage

Run with vMLX (recommended — honors the per-module mixed-precision JANG overrides) or an MLX runtime with Laguna support.

Recommended sampling (vendor defaults): temperature 1.0, top_p 1.0, top_k 20. Stop tokens eos_token_id = [2, 24] (id 24 is end-of-turn — keep it in the stop set).

# vMLX OpenAI-compatible endpoint
# POST /v1/chat/completions
{
  "model": "dealignai/Laguna-S-2.1-JANG_6M-CRACK",
  "messages": [{"role": "user", "content": "..."}],
  "temperature": 1.0, "top_p": 1.0, "top_k": 20,
  "enable_thinking": true
}

About CRACK

CRACK (Controlled Refusal Ablation via Calibrated Knockouts) removes safety-refusal behavior at the weight level by projecting refusal directions out of the residual-stream writer matrices, with strengths calibrated to preserve reasoning quality 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: 64

Safetensors

Model size

118B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized

Model tree for dealignai/Laguna-S-2.1-JANG_6M-CRACK

Base model

poolside/Laguna-S-2.1

Finetuned

(22)

this model