dealignai/Laguna-XS-2.1-CRACK-GGUF overview

---

license: openmdw-1.1

base_model: poolside/Laguna-XS-2.1

base_model_relation: quantized

pipeline_tag: text-generation

library_name: gguf

language:

- en

- zh

metrics:

- accuracy

tags:

- gguf

- llama.cpp

- quantized

- laguna

- moe

- coding

- agentic

- crack

- abliterated

- uncensored

- reasoning

- tool-use

- conversational

- mmlu

- harmbench

- not-for-all-audiences

extra_gated_prompt: >-

This is a permissive research variant with refusal behaviour removed. Access is

provided for security research, red-teaming, and evaluation. You are responsible

for lawful and ethical use.

extra_gated_fields:

I agree to use this model for lawful research and evaluation only: checkbox

---

<p align="center">

<img src="./dealign_mascot.png" alt="dealign.ai mascot" width="112">&nbsp;&nbsp;&nbsp;

<a href="https://huggingface.co/dealignai"><img src="./dealign_logo.png" alt="dealign.ai" width="440"></a>

</p>

<h1 align="center">Laguna XS 2.1 · CRACK · GGUF</h1>

<p align="center">

<strong>Compact Laguna MoE coding model · llama.cpp GGUF · Q6_K · Q4_K_M · Q2_K</strong><br>

Refusal removed with capability preserved — <strong>0 refusals across HarmBench-320</strong>, MMLU within ~0.6 pts of base

</p>

A permissive research variant of poolside/Laguna-XS-2.1 — the compact member of the Laguna agentic-coding Mixture-of-Experts family — packaged for llama.cpp as GGUF. Refusal behaviour has been removed while the model's coding, reasoning, tool-use, and general knowledge are preserved.

This public card intentionally describes compatibility, evaluation, and limitations only. Internal creation details are not published.

Model details

| Property | Value |

|---|---|

| Base model | poolside/Laguna-XS-2.1 |

| Architecture | Laguna MoE — 256 routed experts + 1 shared, top-8 router |

| Layers | 40 (10 global : 30 sliding-window attention) |

| Hidden size | 2,048 |

| Context | up to 262,144 tokens · thinking and non-thinking modes |

| Format | GGUF for llama.cpp |

| Quant scheme | High-precision attention + router; low-bit routed experts (importance-matrix calibrated) |

| Languages | English, Chinese (+ the base model's full multilingual coverage) |

The tokenizer, Laguna chat template (with <think> reasoning and tool-call support), and generation config are bundled. Requires a recent llama.cpp build with Laguna architecture support.

Quantizations

| File | Bits | Size | Recommended for |

|---|---|---|---|

| Laguna-XS-2.1-CRACK-Q6_K.gguf | ~6-bit | ~28 GB | Highest quality; near-lossless |

| Laguna-XS-2.1-CRACK-Q4_K_M.gguf | ~4-bit | ~21 GB | Best balance — recommended default |

| Laguna-XS-2.1-CRACK-Q2_K.gguf | ~2-bit | ~13 GB | Smallest; runs on modest memory |

All quants use importance-matrix calibration and keep attention and the router at high precision, so quality holds up even at 2-bit.

Evaluation

Capability is preserved — MMLU-logit accuracy, each quant vs the unmodified base at the same quant (full 14,042-question test, reasoning off):

| Quant | Base | CRACK | Δ |

|---|---|---|---|

| Q6_K | 73.24% | 73.77% | +0.53 |

| Q4_K_M | 73.54% | 73.63% | +0.09 |

| Q2_K | 70.18% | 69.58% | −0.60 |

Every quant lands within ~0.6 points of its base — Q6 and Q4 are capability-positive.

<details>

<summary><strong>Per-topic MMLU: CRACK vs base by super-category (click to expand)</strong></summary>

Each cell is the CRACK accuracy with its delta vs the same-quant base (full 14,042 MMLU-logit, reasoning off):

| MMLU category | Q6_K CRACK (Δ) | Q4_K_M CRACK (Δ) | Q2_K CRACK (Δ) |

|---|---|---|---|

| STEM | 70.1 (+0.6) | 69.8 (+0.1) | 67.1 (−1.1) |

| Humanities | 69.4 (+0.8) | 69.5 (+0.5) | 66.2 (+1.0) |

| Social Sciences | 81.9 (−0.1) | 81.6 (−0.6) | 77.1 (−1.3) |

| Other (business, health, misc.) | 75.9 (+0.6) | 75.7 (+0.1) | 69.7 (−1.8) |

| Overall | 73.8 (+0.5) | 73.6 (+0.1) | 69.6 (−0.6) |

Capability holds within ~2 points of base across every topic area, even at 2-bit.

</details>

Refusal is removed — full HarmBench-320 compliance (higher = fewer refusals):

| Quant | HarmBench-320 | Standard | Contextual | Copyright |

|---|---|---|---|---|

| Q6_K | 98.8% (0 refusals) | 98.7% | 98.8% | 98.8% |

| Q4_K_M | 99.1% (0 refusals) | 98.7% | 100% | 98.8% |

| Q2_K | 98.4% (0 refusals) | 100% | 98.8% | 95.0% |

Across all 320 HarmBench behaviours the model produced zero refusals at every quant.

Usage (llama.cpp)

# download one quant
hf download dealignai/Laguna-XS-2.1-CRACK-GGUF Laguna-XS-2.1-CRACK-Q4_K_M.gguf --local-dir .

# run
llama-cli -m Laguna-XS-2.1-CRACK-Q4_K_M.gguf -ngl 99 -c 8192 --jinja \
  -p "Write a Python function to reverse a linked list."

Thinking mode is on by default via the bundled chat template; pass --jinja so llama.cpp applies it.

Limitations & responsible use

This model has had refusal behaviour removed and will attempt to comply with harmful, unsafe, or unethical requests. It is intended for security research, red-teaming, and evaluation. You are solely responsible for lawful and ethical use. Not for all audiences.

Base model © poolside, released under the OpenMDW-1.1 license; this quantized variant inherits that license.