Instructions to use GadflyII/GLM-4.7-Flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GadflyII/GLM-4.7-Flash-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="GadflyII/GLM-4.7-Flash-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GadflyII/GLM-4.7-Flash-NVFP4")
model = AutoModelForCausalLM.from_pretrained("GadflyII/GLM-4.7-Flash-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GadflyII/GLM-4.7-Flash-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GadflyII/GLM-4.7-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": "GadflyII/GLM-4.7-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GadflyII/GLM-4.7-Flash-NVFP4

SGLang

How to use GadflyII/GLM-4.7-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 "GadflyII/GLM-4.7-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": "GadflyII/GLM-4.7-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 "GadflyII/GLM-4.7-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": "GadflyII/GLM-4.7-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GadflyII/GLM-4.7-Flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/GadflyII/GLM-4.7-Flash-NVFP4
```

MTP quality, 47 layer

by Michalea - opened Jan 31

Discussion

Michalea

Jan 31

Thank you so much for your contribution to open-source.

Did you check the MTP quality after this quantization?
Maybe leaving original precision for this last layer would be beneficial, what do you think?

GadflyII

Owner Feb 1

No, I didn't. MTP in vLLM does not work at all if the MTP layer is NVFP4; so I did not test it at all.

I made a new version of this model with MTP, and will upload it as soon as testing is complete. I also changed the calibration scripts a bit and left the MTP layer in BF16 which increased the model size by 446MB, MTP works, and initial testing resulted in 63% acceptance rate (vs. 60% original BF16).

I will reply again as soon as it is uploaded.

Michalea

Feb 2

•

edited Feb 2

Thanks! I am waiting for it so much! :-)

What could you say about throughput FP16/8 vs. NVP4 on Blackwell,

will we notice the speedup and it is about no optimised kernels availability issue in vLLM or something other?

(according to this PR https://github.com/vllm-project/vllm/pull/32520 the speedup is huge for FP4, but only in case of dense models)

GadflyII

Owner Feb 2

•

edited Feb 2

GadflyII/GLM-4.7-Flash-MTP-NVFP4 is up.

Blackwell has native hardware acceleration for FP4, which makes it considerably faster than FP8/BF16.

This morning that merged a PR in my vllm fork that should radically improve performance at larger context windows , give it a shot.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment