Instructions to use local-inference-lab/GLM-5.3-Flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use local-inference-lab/GLM-5.3-Flash-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="local-inference-lab/GLM-5.3-Flash-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("local-inference-lab/GLM-5.3-Flash-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("local-inference-lab/GLM-5.3-Flash-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use local-inference-lab/GLM-5.3-Flash-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "local-inference-lab/GLM-5.3-Flash-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": "local-inference-lab/GLM-5.3-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/local-inference-lab/GLM-5.3-Flash-NVFP4

SGLang

How to use local-inference-lab/GLM-5.3-Flash-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 "local-inference-lab/GLM-5.3-Flash-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": "local-inference-lab/GLM-5.3-Flash-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 "local-inference-lab/GLM-5.3-Flash-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": "local-inference-lab/GLM-5.3-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use local-inference-lab/GLM-5.3-Flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/local-inference-lab/GLM-5.3-Flash-NVFP4
```

lukealonso commited on Sep 2

Commit

db14a19

verified ·

1 Parent(s): 2e8b6da

Reshape lil.yaml into serving, kernels, speculators, and override sections

Browse files

The manifest carries only serving policy, kernel selection, speculators, and conditional launch layers. Architectures, attention heads, stored size, and MTP expert quantization are read by the launcher from config.json and the shard sizes at the resolved commit.

Files changed (1) hide show

lil.yaml +22 -29

lil.yaml CHANGED Viewed

@@ -1,32 +1,25 @@
 schema_version: 1
 kind: model
-extends: glm
 description: GLM-5.3 Flash with NVFP4 routed experts and an MXFP8 MTP expert layer
-weight_bytes: 198042331512
-served_model_name: zai-org/GLM-5.3-Flash
-expected_architectures:
-  - Glm5NextForConditionalGeneration
-quantization: modelopt_mixed
-block_size: 256
-disable_flashinfer_autotune: true
-default_speculator: mtp
-mtp_tokens: 5
-dflash2_tokens: 7
-mtp_attention_backend: B12X
-mm_encoder_tp_mode: data
-mm_processor_cache_gb: 0
-launch:
-  local:
-    default_tp_size: 4
-    defaults:
-      environment:
-        INSTANTTENSOR_BUFFER_SIZE: "67108864"
-        INSTANTTENSOR_CHUNK_SIZE: "8388608"
-  spark_rdma:
-    default_tp_size: all
-    defaults:
-      environment:
-        INSTANTTENSOR_BUFFER_SIZE: "67108864"
-        INSTANTTENSOR_CHUNK_SIZE: "8388608"
-mtp_moe_quantization: mxfp8
-dflash2_model: local-inference-lab/GLM-5.3-Flash-DFlash2-MXFP8

 schema_version: 1
 kind: model
+family: glm
 description: GLM-5.3 Flash with NVFP4 routed experts and an MXFP8 MTP expert layer
+serving:
+  served_model_name: zai-org/GLM-5.3-Flash
+  multimodal:
+    encoder_tp_mode: data
+    processor_cache_gb: 0
+kernels:
+  quantization: modelopt_mixed
+  block_size: 256
+  flashinfer_autotune: false
+speculators:
+  default: mtp
+  mtp:
+    tokens: 5
+    moe_quantization: mxfp8
+    attention: B12X
+  dflash:
+    tokens: 7
+    model: local-inference-lab/GLM-5.3-Flash-DFlash2-MXFP8
+environment:
+  INSTANTTENSOR_BUFFER_SIZE: "67108864"
+  INSTANTTENSOR_CHUNK_SIZE: "8388608"