Instructions to use CosmicRaisins/GLM-5.2-MTP-INT4-15pct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CosmicRaisins/GLM-5.2-MTP-INT4-15pct with Transformers:

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

pipe = pipeline("text-generation", model="CosmicRaisins/GLM-5.2-MTP-INT4-15pct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CosmicRaisins/GLM-5.2-MTP-INT4-15pct")
model = AutoModelForCausalLM.from_pretrained("CosmicRaisins/GLM-5.2-MTP-INT4-15pct", 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 CosmicRaisins/GLM-5.2-MTP-INT4-15pct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CosmicRaisins/GLM-5.2-MTP-INT4-15pct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CosmicRaisins/GLM-5.2-MTP-INT4-15pct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CosmicRaisins/GLM-5.2-MTP-INT4-15pct

SGLang

How to use CosmicRaisins/GLM-5.2-MTP-INT4-15pct 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 "CosmicRaisins/GLM-5.2-MTP-INT4-15pct" \
    --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": "CosmicRaisins/GLM-5.2-MTP-INT4-15pct",
		"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 "CosmicRaisins/GLM-5.2-MTP-INT4-15pct" \
        --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": "CosmicRaisins/GLM-5.2-MTP-INT4-15pct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CosmicRaisins/GLM-5.2-MTP-INT4-15pct with Docker Model Runner:
```
docker model run hf.co/CosmicRaisins/GLM-5.2-MTP-INT4-15pct
```

GLM-5.2-MTP-INT4-aligned

Separate-draft MTP (multi-token-prediction) head for speculative decoding with CosmicRaisins/GLM-5.2-AWQ-INT4-15pct. cyankiwi/GLM-5.2-AWQ-INT4 drops GLM-5.2's native MTP layer, so this reconstructs it as a standalone INT4 draft that vLLM loads via --speculative-config (which also sidesteps vLLM #35041 / #38494). INT4 compressed-tensors, single MTP layer, 218 experts to match the pruned target. ~4.8 GB.

Use

--speculative-config '{"model":"CosmicRaisins/GLM-5.2-MTP-INT4-aligned","method":"mtp","num_speculative_tokens":3,"attention_backend":"FLASHMLA_SPARSE"}'

k=3 benched best for me on a synthetic corpus; Z.ai recommends k=5, and I haven't compared them in real-world use yet. Serving stack: github.com/CosmicRaisins/glm-5.2-gb10.

Lineage & license

The MTP weights trace to GLM-5.2's native MTP head (Z.ai, MIT), sourced via 0xSero's NVFP4 layer-78 (0xSero/GLM-5.2-NVFP4-REAP-469B), then dequantized, re-quantized to INT4, expert-pruned to 218, and aligned to the DeepSeekMTP loader layout. The reconstruction and alignment are mine.

License MIT, inherited from the GLM-5.2 base: the MTP weights carry GLM-5.2's MIT grant through 0xSero's quantization (0xSero's repo declares no explicit license). Attributed to Z.ai and 0xSero; not affiliated with either.

Downloads last month: 26

Safetensors

Model size

9B params

Tensor type

I64

F32

I32

BF16

Model tree for CosmicRaisins/GLM-5.2-MTP-INT4-15pct

Base model

zai-org/GLM-5.2

Quantized

cyankiwi/GLM-5.2-AWQ-INT4

Quantized

CosmicRaisins/GLM-5.2-AWQ-INT4-15pct

Quantized

(1)

this model