Instructions to use Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16")
model = AutoModelForCausalLM.from_pretrained("Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16", 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 Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16

SGLang

How to use Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16 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 "Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16" \
    --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": "Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16",
		"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 "Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16" \
        --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": "Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16 with Docker Model Runner:
```
docker model run hf.co/Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GLM-5.3-SUPER SCARY ACORDING TO ANTHROPIC-BF16

Enterprise de-risked GLM-5.3 · 753B Mixture-of-Experts · BF16 master

Built by Blackfrost · Las Vegas, Nevada

FREE THANKS TO ANTHROPIC LYING ON OUR MODELS

Weights published: the verified BF16 checkpoint is available as 158 model shards plus three preserved MTP shards, with its configuration, tokenizer, generation settings, and native GLM chat template.

Intended audience

Access is intended for security firms, authorized red teams, AI-safety labs, guardrail and detection teams, and enterprise research groups operating in controlled environments.

Overview

GLM-5.3-DERISKED-BF16 is Blackfrost's full-precision, weight-level de-risked build of the official zai-org/GLM-5.3-BF16 checkpoint. It is the master artifact for the Blackfrost GLM-5.3 release family.

The intended behavior is intrinsic to the checkpoint. It does not depend on a system prompt, adapter, or decoding-time filter. Production methods are proprietary and are not disclosed.

Specifications


Architecture	`GlmMoeDsaForCausalLM`
Parameters	Approximately 753B stored parameters · Mixture-of-Experts
Precision	BF16 mixed with native FP32 metadata tensors
Artifact size	1,506,659,919,872 indexed tensor bytes (~1.37 TiB)
Shards	158 model shards + 3 MTP shards
Layers	78 main layers + 1 multi-token-prediction layer
Experts	256 routed experts · top-8 active per token · shared expert
Hidden size	6,144
Attention heads	64
Context ceiling	1,048,576 positions
Vocabulary	154,880
Languages	English and Chinese

Tokenizer, generation configuration, and the native GLM chat template are part of the release artifact. Deploy with a runtime that supports GLM-5.3's native reasoning and tool-call tokens.

Lineage


Upstream	`zai-org/GLM-5.3-BF16`
Blackfrost change	Proprietary weight-level de-risking
Not applied	Additional SFT · DPO · RLHF · expert pruning · quantization
Format	Hugging Face Safetensors · BF16

zai-org/GLM-5.3-BF16
  └─ GLM-5.3-DERISKED-BF16              ← this repository
       └─ GLM-5.3-DERISKED-NVFP4        deployment derivative

Validation status

The BF16 artifact passed structural and index-level integrity checks across all 59,585 tensors. The multi-token-prediction layer is present in the release.

No refusal-rate or capability score is claimed in this card before completion of the final judged evaluation. Results will be added only after qualification.

Deployment notes

Plan capacity from the indexed 1.37 TiB weight footprint and reserve additional HBM for KV cache, activations, runtime workspaces, and CUDA graphs.
Use a current serving stack with native GlmMoeDsaForCausalLM support.
The architectural context ceiling is not a guaranteed per-request allocation; set the production context budget from available KV memory.
Treat multi-token prediction as an optional optimization and qualify it independently in the selected runtime.
GLM-5.3's recommended sampling baseline is temperature 1.0 and top-p 0.95.

License and support

Recipients remain responsible for compliance with applicable upstream terms, export controls, local law, and their own authorization boundaries. The upstream checkpoint remains subject to the GLM-5.3 License.

For air-gapped deployment, enterprise support, evaluation services, or a custom build, contact @Blackfrost_AI.

Responsible use

This checkpoint is intended for authorized security testing, AI-safety and alignment research, model evaluation, and defensive engineering. It is not a safety-stock model. Operators must provide independent access control, logging, monitoring, and policy enforcement, and must treat model output as untrusted.

The model is provided as is, without warranty. Evaluation results describe specific test conditions and are not safety certifications or guarantees of behavior in another deployment.

Downloads last month: 366

Safetensors

Model size

753B params

Tensor type

F32

BF16

Model tree for Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16

Base model

zai-org/GLM-5.3-BF16

Finetuned

(1)

this model

Quantizations

1 model