Instructions to use RESMP-DEV/GLM-4.6-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RESMP-DEV/GLM-4.6-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="RESMP-DEV/GLM-4.6-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RESMP-DEV/GLM-4.6-NVFP4")
model = AutoModelForCausalLM.from_pretrained("RESMP-DEV/GLM-4.6-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 RESMP-DEV/GLM-4.6-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RESMP-DEV/GLM-4.6-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": "RESMP-DEV/GLM-4.6-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RESMP-DEV/GLM-4.6-NVFP4

SGLang

How to use RESMP-DEV/GLM-4.6-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 "RESMP-DEV/GLM-4.6-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": "RESMP-DEV/GLM-4.6-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 "RESMP-DEV/GLM-4.6-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": "RESMP-DEV/GLM-4.6-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RESMP-DEV/GLM-4.6-NVFP4 with Docker Model Runner:
```
docker model run hf.co/RESMP-DEV/GLM-4.6-NVFP4
```

GLM-4.6-NVFP4

Quantized version of GLM-4.6 using LLM Compressor and the NVFP4 (E2M1 + E4M3) format.

This time it actually works! We think

This should be the start of a new series of hopefully optimal NVFP4 quantizations as capable cards continue to grow out in the wild.

Model Summary

Property	Value
Base model	GLM-4.6
Quantization	NVFP4 (FP4 microscaling, block = 16, scale = E4M3)
Method	Post-Training Quantization with LLM Compressor
Toolchain	LLM Compressor
Hardware target	NVIDIA Blackwell (Untested on RTX cards) / GB200 Tensor Cores
Precision	Weights & activations = FP4 • Scales = FP8 (E4M3)
Maintainer	REMSP.DEV

Description

This model is a drop-in replacement for GLM-4.6 that runs in NVFP4 precision, enabling up to 6× faster GEMM throughput and around 65 % lower memory use compared with BF16. Accuracy remains within ≈ 1 % of the FP8 baseline on standard reasoning and coding benchmarks.

Downloads last month: 47

Safetensors

Model size

199B params

Tensor type

BF16

F32

F8_E4M3

Model tree for RESMP-DEV/GLM-4.6-NVFP4

Base model

zai-org/GLM-4.6

Quantized

(40)

this model