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

Libraries

How to use Inferact/GLM-5.3-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="Inferact/GLM-5.3-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Inferact/GLM-5.3-NVFP4")
model = AutoModelForCausalLM.from_pretrained("Inferact/GLM-5.3-NVFP4", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Inferact/GLM-5.3-NVFP4 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Inferact/GLM-5.3-NVFP4

SGLang

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

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

Fidelity measurement: KL(reference || this quant) on frozen tokens, receipt-backed

by malaiwah - opened Sep 5

Discussion

malaiwah

Sep 5

What this is. A third-party fidelity measurement of Inferact/GLM-5.3-NVFP4 @ ce67b36f3669192b5bb233819f0fda6c8a9837f8 (nvfp4, 4 bits per weight as declared) against its unquantized reference, made with quant-fidelity-suite. Measured by malaiwah, not by the model's author. Every number below is read from a sealed receipt named at the bottom.


KL(reference ‖ candidate), mean tokenwise, nats	0.07542936216471374
top-1 agreement	0.9239472398632145
KL median / p95 / p99 / max	0.004894225019666099 / 0.35061047642682547 / 1.249190350210349 / 8.380735342841277
reference root dataset	`malaiwah/glm53-fidelity-root-v1` @ `9c4a29ee10f393ed2fdbdb9262c1192ddb1507b4` (capture `9eba97dddb4ff2e2…`)
panel	`panel--glm53.malaiwah.corpus5x5-v1`, 25 contexts, 51175 scored positions
direction / vocabulary / accumulation	KL(reference
method	dequantize-and-run, weights only: `nvfp4-modelopt-dequant-to-bf16` -- the ModelOpt NVFP4 dialect (quant_algo NVFP4, producer undeclared): each routed-expert projection's packed e2m1 nibbles (group 16 along the input axis) are decoded to exact fp32 as e2m1 x weight_scale.f32 x weight_scale_2 on the capture device and cast once to bf16 under the official tensor name, bitwise the compressed-tensors reference on real fetched rows; routed experts only -- every non-routed tensor is carried as shipped (plain bf16 under the official names); the per-tensor `input_scale` is an activation quantity and is NOT applied (static-nvfp4-not-applied), so the measurement is weights-only; same engine, schedule and device as the reference capture
determinism	two fresh processes captured the candidate; both sealed captures carry content digest `83d9cd978e771583…` (self-comparison 0.0)
comparability class	advisory

Disclosures on the comparison receipt:

native_head_replay (info): HEAD-1d: each side replayed through its own sealed head (reference 864f488a0074, candidate 864f488a0074); head error is inside the measurement, as under HEAD-2, and nothing is substituted. The heads are content-identical.
activation_quantization_not_captured (caveat): candidate was captured from a bf16 materialisation of its weights (nvfp4-modelopt-dequant-to-bf16); the checkpoint declares activation quantization (static-nvfp4-not-applied) that a weights-only capture does not apply, so a served deployment also quantizes activations at runtime. That term is not in this number, which is expected to understate the served divergence; it is not a mathematical bound. The comparison is advisory.

What this number does not do. It is a same-lane distance from one reference capture on one panel. It does not rank this artifact against numbers measured on another panel, lane or reference, and a same-lane root does not retroactively upgrade rows measured against another teacher. Per-window scatter exceeds the gap between adjacent bit-widths; compare only within a group whose comparability keys match.

Receipts.

comparison receipt receipt_sha256 186fa1df288d25f7f097dd9aa0b7830df840f1656e54732d460b2e9c71bf4fc0
root-qualification receipt receipt_sha256 91a0abe2cab52e4968f95b21481df99c2480ebbb9b4499c1620f16ea67bc003a (canonical dataset_sha256 f5f8fe3dcc721e28aa00d02b428258c2121fca7c6fa659b1f51d444777e10e8e, repeat 392c7690ad52bed3a3db3484910301aa6f2a8421324c0471d510e55b3726a73d)
job job_id_full b46b546acb7224fa2a0435752b57898854b2cbc7bc6d73a3d264e38c908acda1
candidate capture dataset published: malaiwah/glm53-fidelity-nvfp4-inferact-v1 @ 25a1865187fc727989bb2c32dde49c63292370c2

Reproduce: fetch the two datasets named above and run fidelity-dataset compare --reference <root> --candidate <this> --own-heads; the receipt's estimator block is the exact recipe. Questions and corrections are welcome here; the registry files this as a third-party row (measured_by enumerated, never conflated with author-reported numbers).

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