[!IMPORTANT] Set your sampler explicitly: temperature=1.0, top_p=1.0, top_k=20 — the poolside vendor defaults documented for Laguna XS 2.1. These values are baked into generation_config.json and jang_config.json → sampling_defaults, but many inference runtimes ignore those files and fall back to no top_k filter, which produces incoherent / degraded output on this model. Pass them explicitly at your API request layer or CLI flags.

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}

Laguna-XS 2.1 — JANG_6M CRACK

CRACK abliterated · JANG mixed-precision (MLX affine) · Agentic coding · Reasoning toggle · Tool calling · 262K context · ~26 GB

Ko-fi

What Is This?

This is poolside/Laguna-XS-2.1 — a 33B-parameter / ~3B-active Mixture-of-Experts model (40 layers, 256 routed experts top-8 + 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 — mixed-precision affine MLX bundle tuned for Apple Silicon (~26 GB). High-precision attention, shared expert, router, and norms; the routed-expert bulk carries the low-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)	73.6%	73.4%
HarmBench-320 (compliance / ASR)	—	99.4% (318/320)

Abliteration is essentially capability-neutral — MMLU moves −0.2 points, within run-to-run noise. The model stays coherent in both direct and reasoning modes.

HarmBench by category

Category	Compliance
Standard	100% (159/159)
Copyright	100% (80/80)
Contextual	98% (79/81)
Overall	99.4% (318/320)

Features

Agentic coding — Laguna-XS'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).

python

# vMLX OpenAI-compatible endpoint
# POST /v1/chat/completions
{
  "model": "dealignai/Laguna-XS-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.