Instructions to use brandonmusic/GLM-5.3-Flash-tr3-4bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brandonmusic/GLM-5.3-Flash-tr3-4bpw with Transformers:

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

pipe = pipeline("image-text-to-text", model="brandonmusic/GLM-5.3-Flash-tr3-4bpw")
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("brandonmusic/GLM-5.3-Flash-tr3-4bpw")
model = AutoModelForMultimodalLM.from_pretrained("brandonmusic/GLM-5.3-Flash-tr3-4bpw", 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 brandonmusic/GLM-5.3-Flash-tr3-4bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brandonmusic/GLM-5.3-Flash-tr3-4bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brandonmusic/GLM-5.3-Flash-tr3-4bpw",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/brandonmusic/GLM-5.3-Flash-tr3-4bpw

SGLang

How to use brandonmusic/GLM-5.3-Flash-tr3-4bpw 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 "brandonmusic/GLM-5.3-Flash-tr3-4bpw" \
    --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": "brandonmusic/GLM-5.3-Flash-tr3-4bpw",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "brandonmusic/GLM-5.3-Flash-tr3-4bpw" \
        --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": "brandonmusic/GLM-5.3-Flash-tr3-4bpw",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use brandonmusic/GLM-5.3-Flash-tr3-4bpw with Docker Model Runner:
```
docker model run hf.co/brandonmusic/GLM-5.3-Flash-tr3-4bpw
```

brandonmusic commited on Aug 27

Commit

4739eb1

verified ·

1 Parent(s): 4bccf1b

Link complete BF16 teacher logits dataset

Browse files

Files changed (1) hide show

README.md +18 -0

README.md CHANGED Viewed

@@ -20,6 +20,24 @@ The direct packed TP2 serving result (`0.022750847878`) is a separate one-window
 Code and the five-run receipts: [brandonmmusic-max/glm-5.3-flash-exl3-4bpw](https://github.com/brandonmmusic-max/glm-5.3-flash-exl3-4bpw).
 ## Minimal TP2 launch
 Note this is NOT an optimize launch nearly at all.  I woudl recommend trying https://github.com/chriswritescode-dev/glm-5.3-flash-sm120 image referenced
 here.  that use the MLA which compresses the latent before you get to kv_b_proj.  Getting that running you might get 1 million kv cache.

 Code and the five-run receipts: [brandonmmusic-max/glm-5.3-flash-exl3-4bpw](https://github.com/brandonmmusic-max/glm-5.3-flash-exl3-4bpw).
+## BF16 teacher logits and replay calibration
+The complete teacher dataset is published at
+[`brandonmusic/GLM-5.3-Flash-BF16-Teacher-Logits`](https://huggingface.co/datasets/brandonmusic/GLM-5.3-Flash-BF16-Teacher-Logits).
+It contains 640 rolling calibration windows plus the 25 qualification-only final
+windows: 665 windows total, each with 2,048 input tokens, 2,047 scored positions,
+and the full 154,880-token vocabulary. The 1,361,255 scored positions occupy
+843,324,965,136 raw logits bytes.
+The teacher is the released BF16 checkpoint with its native FP32 tensors
+preserved; the logits are stored as float32 to avoid an additional
+storage-precision loss. Payload revision
+[`7c378d5f17dba158c4c803eff27c346dd0615660`](https://huggingface.co/datasets/brandonmusic/GLM-5.3-Flash-BF16-Teacher-Logits/tree/7c378d5f17dba158c4c803eff27c346dd0615660)
+is bound by the
+[`16e16e90078bc0b54bd1cd37b08ba7dad03819726d0258443a0e30b68b354472` aggregate audit](https://huggingface.co/datasets/brandonmusic/GLM-5.3-Flash-BF16-Teacher-Logits/blob/267ccf27ca92575529e0a1ef80e7eed8d209a8f4/logits/full-panel/receipts/full-dataset-audit.json),
+which records every payload path, size, and SHA-256. The 25 final windows remain
+qualification-only and are excluded from fitting and expert selection.
 ## Minimal TP2 launch
 Note this is NOT an optimize launch nearly at all.  I woudl recommend trying https://github.com/chriswritescode-dev/glm-5.3-flash-sm120 image referenced
 here.  that use the MLA which compresses the latent before you get to kv_b_proj.  Getting that running you might get 1 million kv cache.