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

Libraries

How to use Mapika/GLM-5.2-NVFP4 with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Mapika/GLM-5.2-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("Mapika/GLM-5.2-NVFP4")
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]:]))

TensorRT

How to use Mapika/GLM-5.2-NVFP4 with TensorRT:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mapika/GLM-5.2-NVFP4 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Mapika/GLM-5.2-NVFP4

SGLang

How to use Mapika/GLM-5.2-NVFP4 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 "Mapika/GLM-5.2-NVFP4" \
    --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": "Mapika/GLM-5.2-NVFP4",
		"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 "Mapika/GLM-5.2-NVFP4" \
        --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": "Mapika/GLM-5.2-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

GLM-5.2-NVFP4

NVFP4 (4-bit) quantization of zai-org/GLM-5.2, produced with NVIDIA TensorRT Model Optimizer 0.44.0. The MoE expert FFNs (routed + shared) are quantized to NVFP4; attention (MLA + the DeepSeek-style DSA lightning indexer), the router, and the LM head are kept in BF16. This shrinks the checkpoint from 1.5 TB → 410 GB (~3.7×) while retaining GSM8K accuracy within ~2 points of BF16.

GLM-5.2 is a glm_moe_dsa model: DeepSeek-V3.2-style MLA attention + DSA sparse-attention indexer, with a 256-routed-expert + 1-shared-expert MoE (8 experts/token), 78 layers, hidden 6144, vocab 154880.

Evaluation

All benchmarks were served via SGLang and scored with lm-evaluation-harness on the same hardware and harness for both NVFP4 and BF16 (generative / chain-of-thought where applicable; max_gen_toks raised to fit the reasoning chains — lm-eval's default 256 truncates them and tanks the scores).

Benchmark	GLM-5.2-NVFP4 (410 GB)	GLM-5.2 BF16 (1507 GB)	Δ
GPQA-Diamond (CoT, flexible)	69.70	69.70	0.00
MATH-500 (minerva)	86.80	86.60	+0.20
MMLU-Pro (generative, 50/subject)	81.14	82.43	−1.29
HumanEval (pass@1, instruct)	94.51	95.73	−1.22
GSM8K (5-shot, flexible)	92.72	94.92	−2.20

NVFP4 holds up strongly on the hard, non-saturated benchmarks: GPQA-Diamond and MATH-500 are within noise of BF16, and the average degradation across the suite is ~1 point — for a 3.7× smaller checkpoint.

Quantization recipe

Format: NVFP4 (FP4 weights + FP8 block scales), block/group size 16, modelopt producer.
Quantized: mlp.experts.* (256 routed experts) and mlp.shared_experts.*.
Kept in BF16 (excluded): all of self_attn.* — MLA projections (q/kv) and the DSA indexer — plus the MoE router (mlp.gate) and lm_head. The indexer and MLA attention must stay BF16: SGLang's deepseek_v2 MLA path (used for glm_moe_dsa) cannot consume NVFP4 attention weights.
KV cache: not quantized.
Calibration: 512 samples × 2048 tokens from cnn_dailymail + nvidia/OpenCodeReasoning + nvidia/OpenMathReasoning.

Serving (SGLang)

Requires SGLang ≥ v0.5.13.post1 (the version that registers GlmMoeDsaForCausalLM).

docker run --runtime=nvidia --gpus '"device=0,1,2,3"' --ipc=host --shm-size=32g \
  -v /path/to/GLM-5.2-NVFP4:/model -p 30000:30000 \
  lmsysorg/sglang:v0.5.13.post1-cu130 \
  sglang serve --model-path /model --tp 4 \
    --quantization modelopt_fp4 --moe-runner-backend flashinfer_cutlass \
    --context-length 32768 --mem-fraction-static 0.85 \
    --tool-call-parser auto --trust-remote-code --host 0.0.0.0 --port 30000

GPU memory. The weights are ~410 GB, so per-GPU footprint depends on TP:

Tensor parallel	Weights / GPU	Suitable GPUs
`--tp 4`	~110 GB	≥128 GB cards — H200 (141 GB, tight KV), B200 / B300, MI300X (192 GB)
`--tp 8`	~55 GB	80 GB cards — 8× H100 or A100-80GB

So 80 GB GPUs need --tp 8, not --tp 4 (110 GB of weights can't fit in an 80 GB card). Lower --mem-fraction-static if KV-cache space is tight. Use a generous max_tokens at inference — GLM-5.2 is a reasoning model and its <think> chains can be long.

Notes

Quantized with nvfp4 + a small build_quant_cfg exclusion that keeps self_attn.* in BF16 (required for SGLang's MLA path). Same overall pipeline as our MiniMax-M3-NVFP4.
License inherited from the base model (MIT, Zhipu AI).

Downloads last month: -

Safetensors

Model size

379B params

Tensor type

BF16

F32

F8_E4M3

Model tree for Mapika/GLM-5.2-NVFP4

Base model

zai-org/GLM-5.2

Quantized

(16)

this model