Instructions to use inference-optimization/GLM-5.3-Flash-0.1B-A0.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inference-optimization/GLM-5.3-Flash-0.1B-A0.1B with Transformers:

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

pipe = pipeline("image-text-to-text", model="inference-optimization/GLM-5.3-Flash-0.1B-A0.1B")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("inference-optimization/GLM-5.3-Flash-0.1B-A0.1B")
model = AutoModelForMultimodalLM.from_pretrained("inference-optimization/GLM-5.3-Flash-0.1B-A0.1B", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inference-optimization/GLM-5.3-Flash-0.1B-A0.1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inference-optimization/GLM-5.3-Flash-0.1B-A0.1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inference-optimization/GLM-5.3-Flash-0.1B-A0.1B",
		"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/inference-optimization/GLM-5.3-Flash-0.1B-A0.1B

SGLang

How to use inference-optimization/GLM-5.3-Flash-0.1B-A0.1B 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 "inference-optimization/GLM-5.3-Flash-0.1B-A0.1B" \
    --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": "inference-optimization/GLM-5.3-Flash-0.1B-A0.1B",
		"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 "inference-optimization/GLM-5.3-Flash-0.1B-A0.1B" \
        --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": "inference-optimization/GLM-5.3-Flash-0.1B-A0.1B",
		"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 inference-optimization/GLM-5.3-Flash-0.1B-A0.1B with Docker Model Runner:
```
docker model run hf.co/inference-optimization/GLM-5.3-Flash-0.1B-A0.1B
```

GLM-5.3-Flash-0.1B-A0.1B / README.md

kylesayrs

Upload folder using huggingface_hub

7c3a6d3 verified 1 day ago

preview code

Raw

History Blame Contribute Delete

4.88 kB

	---
	license: mit
	base_model:
	- zai-org/GLM-5.3-Flash
	library_name: transformers
	---

	# GLM-5.3-Flash-0.1B-A0.1B

	This is a tiny version of [zai-org/GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash) created for testing and development.

	## Model Details

	- Base Model: zai-org/GLM-5.3-Flash
	- Architecture: glm5_next (`Glm5NextForConditionalGeneration`)
	- Total Parameters: 0.084B
	- Activated Parameters: 0.084B (MoE: 4 of 8 routed experts + 1 shared expert per sparse layer)

	This tiny model preserves the full architecture of the base model:
	- Hybrid attention: KDA linear attention (`linear_attention`) layers and DeepSeek sparse attention / MLA (`deepseek_sparse_attention`) layers with the token indexer.
	- Mixed FFN schedule: dense MLP layers (first 3) and sparse MoE layers (routed experts + shared expert).
	- Manifold-Constrained Hyper-Connections (mHC) at every attention/FFN site.
	- The vision tower (`Glm5NextVisionModel`) and multimodal projector.

	The model is a bf16 dense checkpoint (the base model's fp8 `quantization_config` was removed so the tiny model can be randomly initialized and fine-tuned).

	## Configuration Changes

	The following parameters were reduced from the original model:

	\| Parameter \| Original \| Tiny \|
	\|---\|---\|---\|
	\| text `hidden_size` \| 4096 \| 256 \|
	\| text `num_hidden_layers` \| 45 \| 5 \|
	\| text `intermediate_size` (dense) \| 12288 \| 256 \|
	\| text `moe_intermediate_size` \| 2048 \| 128 \|
	\| `n_routed_experts` \| 288 \| 8 \|
	\| `num_experts_per_tok` \| 8 \| 4 \|
	\| `n_shared_experts` \| 1 \| 1 \|
	\| `num_attention_heads` / `num_key_value_heads` \| 64 \| 4 \|
	\| `q_lora_rank` \| 1536 \| 128 \|
	\| `kv_lora_rank` \| 512 \| 64 \|
	\| `qk_nope_head_dim` / `v_head_dim` \| 256 \| 64 \|
	\| `index_n_heads` \| 32 \| 4 \|
	\| `index_head_dim` \| 128 \| 64 \|
	\| `index_topk` \| 2048 \| 64 \|
	\| `index_kpool` \| 4 \| 4 \|
	\| linear attn `num_heads` \| 64 \| 4 \|
	\| vision `depth` \| 24 \| 2 \|
	\| vision `hidden_size` \| 1024 \| 128 \|
	\| vision `out_hidden_size` \| 4096 \| 256 \|
	\| `vocab_size` \| 154880 \| 154880 (unchanged) \|
	\| quantization \| fp8 (block 128×128) \| none (bf16) \|

	Per-layer schedules were regenerated for the reduced depth:
	- `layer_types`: `[linear, linear, linear, deepseek_sparse_attention, linear]`
	- `mlp_layer_types`: `[dense, dense, dense, sparse, sparse]`
	- `indexer_types`: `[full, full, full, full, full]`

	## Checkpoint Structure

	Single-file `model.safetensors` (223 tensors). The tensor naming is analogous to the
	original sharded checkpoint (`model.language_model.layers.`, `model.visual.`,
	`lm_head.weight`, hyper-connection params `hc_attn_` / `hc_ffn_`, MLA params
	`q_a_proj`/`q_b_proj`/`kv_a_proj_with_mqa`/`kv_b_proj`, indexer params, KDA linear-attention
	params, and packed MoE `mlp.experts.*`).

	Two intentional differences vs. the original:
	- No `weight_scale_inv` tensors — the tiny model is bf16, not fp8.
	- No MTP layer (original layer index 45 with `eh_proj`/`enorm`/`hnorm`/`shared_head.norm`)
	— the transformers `Glm5Next` model does not build the multi-token-prediction layer
	(`_keys_to_ignore_on_load_unexpected` skips `layers.45.*`), so no converter is required.

	## Usage

	```python
	from transformers import Glm5NextForConditionalGeneration, AutoTokenizer

	model = Glm5NextForConditionalGeneration.from_pretrained(
	"inference-optimization/GLM-5.3-Flash-0.1B-A0.1B", device_map="auto"
	)
	tokenizer = AutoTokenizer.from_pretrained("inference-optimization/GLM-5.3-Flash-0.1B-A0.1B")

	input_ids = tokenizer("According to all known laws", return_tensors="pt").input_ids.to(model.device)
	output = model.generate(input_ids, max_new_tokens=20)
	print(tokenizer.decode(output[0]))
	```

	## Creation Process

	This model was created using the llm-compressor `create-tiny-model` claude skill.

	1. Built a reduced `Glm5NextConfig` from the base config (removed `quantization_config`; shrank hidden/layer/expert/MLA/indexer/vision dims; regenerated per-layer schedules).
	2. Randomly initialized weights (`init_weights` + non-finite/extreme-value fixup) with transformers 5.16.1.
	3. Fine-tuned text-only on a small copypasta dataset until the training perplexity converged well below 3.0.
	4. Verified the saved checkpoint structure matches the original naming convention (minus fp8 scales and the MTP layer).

	## Validation

	```
	perplexity = 1.05 (target <= 10) PASS
	GEN: According to all known laws of aviation, there is no way a bee should be able to fly. Its wings are too small
	total params: 84,361,950
	```

	## Notes

	- Requires `transformers >= 5.16.0` (which registers the `glm5_next` model type).
	- This is a randomly-initialized, fine-tuned-on-toy-data model. It is intended solely for
	testing/development of tooling (quantization, serving, CI) and has no real language or
	vision capability.
	- Fine-tuning was text-only; the vision tower is randomly initialized.