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 16

Commit

175ae8c

verified ·

1 Parent(s): d454812

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -24

README.md CHANGED Viewed

@@ -71,41 +71,19 @@ the unquantized components to compensate alongside the NVFP4 experts.
 ### Training data
 The distillation corpus contains approximately 200M prompt-and-response
-tokens. Prompts cover coding,
-reasoning, instruction following and conversations, including curated
-coding/instruction samples, UltraChat and WildChat inputs. Assistant
-responses come from the BF16 GLM teacher using its native chat template.
-Raw text is used for activation calibration, not distillation training.
 ### Activation calibration
 Distillation uses BF16 activations. For NVFP4 activation quantization at
 inference, expert-specific input scales are calibrated separately on the
-200M-token chat corpus and an additional 100M raw-text tokens. Each stored range
-uses the larger maximum observed across the two corpora.
 Calibration uses natural routing and covers all 12,096 layer/expert pairs
 without fallback scales. Gate/up share their expert's input range; down
 uses the post-activation range. The serving configuration also retains
 dynamic MXFP8 activation quantization for MTP routed experts.
-### Training-path evaluation
-The prompt-disjoint holdout contains 35 chat documents and 114,714 tokens.
-Both measurements use native student routing, NVFP4 expert weights and
-BF16 activations. Lower is better.
-| Metric | Before distillation | Distilled model |
-| --- | ---: | ---: |
-| Nucleus TV | 0.054213 | 0.051114 |
-| Hidden-state MSE | 0.091256 | 0.079682 |
-| Teacher-to-student KL | 0.047267 | 0.043334 |
-These are teacher-agreement measurements on a monitored training holdout,
-not downstream benchmark scores or measurements of NVFP4 activation
-quantization at inference.
 ### Requirements
 Use a runtime supporting the `glm5_next` architecture and this mixed

 ### Training data
 The distillation corpus contains approximately 200M prompt-and-response
+tokens. Assistant responses come from the BF16 GLM teacher using its native chat template.
 ### Activation calibration
 Distillation uses BF16 activations. For NVFP4 activation quantization at
 inference, expert-specific input scales are calibrated separately on the
+200M-token chat corpus.
 Calibration uses natural routing and covers all 12,096 layer/expert pairs
 without fallback scales. Gate/up share their expert's input range; down
 uses the post-activation range. The serving configuration also retains
 dynamic MXFP8 activation quantization for MTP routed experts.
 ### Requirements
 Use a runtime supporting the `glm5_next` architecture and this mixed