Instructions to use dealignai/GLM-5.2-NVFP4-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/GLM-5.2-NVFP4-CRACK with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dealignai/GLM-5.2-NVFP4-CRACK")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dealignai/GLM-5.2-NVFP4-CRACK")
model = AutoModelForCausalLM.from_pretrained("dealignai/GLM-5.2-NVFP4-CRACK", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dealignai/GLM-5.2-NVFP4-CRACK with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dealignai/GLM-5.2-NVFP4-CRACK"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dealignai/GLM-5.2-NVFP4-CRACK",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dealignai/GLM-5.2-NVFP4-CRACK

SGLang

How to use dealignai/GLM-5.2-NVFP4-CRACK with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "dealignai/GLM-5.2-NVFP4-CRACK" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dealignai/GLM-5.2-NVFP4-CRACK",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "dealignai/GLM-5.2-NVFP4-CRACK" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dealignai/GLM-5.2-NVFP4-CRACK",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dealignai/GLM-5.2-NVFP4-CRACK with Docker Model Runner:
```
docker model run hf.co/dealignai/GLM-5.2-NVFP4-CRACK
```

dealign.ai

GLM-5.2-NVFP4-CRACK

Abliterated GLM-5.2 — ~~753B MoE (~~40B active), 180K context, native MTP speculative decoding

320/320 = 100% HarmBench compliance with -1.2% MMLU change. Refusal removed, capability preserved.

Model Details


Source	`nvidia/GLM-5.2-NVFP4`
Architecture	`GlmMoeDsa` — MoE (256 routed + 1 shared / layer), MLA + DSA sparse attention
Parameters	~753B total · ~40B active (top-8 of 256 routed experts + 1 shared)
Precision	NVFP4 (ModelOpt) — routed experts NVFP4, attention/shared bf16
Context	180,224
Speculative decoding	Native MTP (num_speculative_tokens=1)
Abliteration	CRACK (refusal removal)

This is a real modification — not tricks

No system-prompt jailbreaks. No chat-template hacks. No LoRA adapters bolted on. The refusal behavior is changed in the weights themselves, and the model's own reasoning, tool-calling, and coding ability are left fully intact. We don't ship cheap template tricks or throwaway fine-tunes.

Benchmarks

MMLU — knowledge retention (logit-mode, 57 tasks × 18)

	Base	CRACK	Δ
MMLU (overall)	87.5%	86.4%	-1.2%

Full per-subject breakdown (before → after)

Subject	Base	CRACK	Δ
Abstract Algebra	61.1	66.7	+5.6
Anatomy	94.4	94.4	+0.0
Astronomy	94.4	94.4	+0.0
Business Ethics	94.4	88.9	-5.5
Clinical Knowledge	88.9	88.9	+0.0
College Biology	94.4	94.4	+0.0
College Chemistry	72.2	61.1	-11.1
College Computer Science	88.9	77.8	-11.1
College Mathematics	66.7	72.2	+5.5
College Medicine	88.9	88.9	+0.0
College Physics	77.8	77.8	+0.0
Computer Security	83.3	88.9	+5.6
Conceptual Physics	88.9	94.4	+5.5
Econometrics	83.3	83.3	+0.0
Electrical Engineering	83.3	83.3	+0.0
Elementary Mathematics	88.9	88.9	+0.0
Formal Logic	77.8	72.2	-5.6
Global Facts	77.8	72.2	-5.6
High School Biology	94.4	94.4	+0.0
High School Chemistry	77.8	72.2	-5.6
High School Computer Science	88.9	83.3	-5.6
High School European History	88.9	88.9	+0.0
High School Geography	94.4	94.4	+0.0
High School Government And Politics	100.0	100.0	+0.0
High School Macroeconomics	94.4	94.4	+0.0
High School Mathematics	83.3	77.8	-5.5
High School Microeconomics	88.9	88.9	+0.0
High School Physics	83.3	88.9	+5.6
High School Psychology	100.0	100.0	+0.0
High School Statistics	94.4	88.9	-5.5
High School Us History	94.4	94.4	+0.0
High School World History	94.4	94.4	+0.0
Human Aging	83.3	83.3	+0.0
Human Sexuality	88.9	88.9	+0.0
International Law	94.4	94.4	+0.0
Jurisprudence	94.4	88.9	-5.5
Logical Fallacies	83.3	77.8	-5.5
Machine Learning	83.3	72.2	-11.1
Management	88.9	88.9	+0.0
Marketing	100.0	100.0	+0.0
Medical Genetics	94.4	94.4	+0.0
Miscellaneous	94.4	94.4	+0.0
Moral Disputes	83.3	83.3	+0.0
Moral Scenarios	77.8	61.1	-16.7
Nutrition	100.0	100.0	+0.0
Philosophy	100.0	100.0	+0.0
Prehistory	83.3	83.3	+0.0
Professional Accounting	83.3	88.9	+5.6
Professional Law	77.8	83.3	+5.5
Professional Medicine	88.9	94.4	+5.5
Professional Psychology	100.0	100.0	+0.0
Public Relations	72.2	72.2	+0.0
Security Studies	83.3	77.8	-5.5
Sociology	88.9	88.9	+0.0
Us Foreign Policy	100.0	94.4	-5.6
Virology	61.1	61.1	+0.0
World Religions	100.0	100.0	+0.0

HarmBench — refusal removal (HarmBench-320, greedy)

Base GLM-5.2 over-refuses across these categories (the behavior this release corrects). After abliteration:

Category	Compliance	Rate
Chemical / biological	42 / 42	100%
Copyright	80 / 80	100%
Cybercrime / intrusion	52 / 52	100%
Harassment / bullying	21 / 21	100%
Harmful	18 / 18	100%
Illegal	53 / 53	100%
Misinformation	54 / 54	100%
Total	320 / 320	100%

0 incoherent / degenerate outputs. Copyright behaviors are verbatim-reproduction requests (over-refusal), not a safety category.

Coherence & capability ✅

Multi-turn memory, tool-calling (glm47 parser), and working code generation verified.
No loops, no truncation, no degeneration. Decode ~110 tok/s on 4×H200 with MTP.

Serve (vLLM, SM90 / Hopper)

vllm serve dealignai/GLM-5.2-NVFP4-CRACK \
  --tensor-parallel-size 4 \
  --kv-cache-dtype bfloat16 \
  --reasoning-parser glm47 \
  --enable-auto-tool-choice --tool-call-parser glm47 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":1}'

Requires an SM90 build with native NVFP4 Marlin + MoE kernels.

Acknowledgements

Compute for this build was generously provided by @jordanschenck — thank you.

Support dealignai

We research and publish abliterated models to advance AI safety understanding — built from original research and published free.

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

Ko-fi | 𝕏 @dealignai | dealign.ai

Provided for research. Users are responsible for compliance with applicable laws and regulations.

Downloads last month: 95

Safetensors

Model size

381B params

Tensor type

F32

BF16

Model tree for dealignai/GLM-5.2-NVFP4-CRACK

Base model

zai-org/GLM-5.2

Quantized

nvidia/GLM-5.2-NVFP4

Finetuned

(4)

this model