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

Libraries

How to use nota-ai/GLM-5.3-Flash-Nota-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="nota-ai/GLM-5.3-Flash-Nota-NVFP4")
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("nota-ai/GLM-5.3-Flash-Nota-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("nota-ai/GLM-5.3-Flash-Nota-NVFP4", 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 nota-ai/GLM-5.3-Flash-Nota-NVFP4 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nota-ai/GLM-5.3-Flash-Nota-NVFP4

SGLang

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

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

GLM-5.3-Flash-Nota-NVFP4 / config.json

hancheolp

Upload folder using huggingface_hub

1090318 verified 18 days ago

Raw

History Blame Contribute Delete

10.8 kB

	{
	"architectures": [
	"Glm5NextForConditionalGeneration"
	],
	"dtype": "bfloat16",
	"image_end_token_id": 154831,
	"image_start_token_id": 154830,
	"image_token_id": 154854,
	"model_type": "glm5_next",
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "nvfp4-pack-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": "local",
	"group_size": 16,
	"num_bits": 4,
	"observer": "static_minmax",
	"observer_kwargs": {},
	"scale_dtype": "torch.float8_e4m3fn",
	"strategy": "tensor_group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": 16,
	"num_bits": 4,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": "torch.float8_e4m3fn",
	"strategy": "tensor_group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	}
	},
	"format": "nvfp4-pack-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"re:.self_attn.",
	"re:.model\\.visual.",
	"re:.shared_experts.",
	"re:.q_a_proj.",
	"re:.kv_a_proj_with_mqa.",
	"re:.lm_head.",
	"re:.embed_tokens.",
	"re:.indexer.",
	"re:.kv_b_proj.",
	"re:.eh_proj.",
	"re:.shared_head.",
	"re:.f_a_proj.",
	"re:.f_b_proj.",
	"re:.g_a_proj.",
	"re:.g_b_proj.",
	"re:.\\.b_proj.",
	"re:.layers\\.0\\.mlp.",
	"re:.layers\\.1\\.mlp.",
	"re:.layers\\.2\\.mlp.",
	"re:.layers\\.45.",
	"re:.model\\.language_model\\.layers\\.10\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.11\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.12\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.13\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.14\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.15\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.16\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.17\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.18\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.19\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.20\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.21\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.22\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.23\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.24\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.25\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.26\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.27\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.28\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.29\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.3\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.30\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.31\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.32\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.33\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.34\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.35\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.36\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.37\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.38\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.39\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.4\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.40\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.41\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.42\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.43\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.44\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.45\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.5\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.6\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.7\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.8\\.mlp\\.gate.",
	"re:.model\\.language_model\\.layers\\.9\\.mlp\\.gate."
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed"
	},
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": [
	154820,
	154827,
	154829
	],
	"first_k_dense_replace": 3,
	"hc_eps": 1e-06,
	"hc_mult": 4,
	"hc_sinkhorn_iters": 20,
	"head_dim": 0,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"index_head_dim": 128,
	"index_kpool": 4,
	"index_kpool_always_select_tail": true,
	"index_kpool_compress": true,
	"index_n_heads": 32,
	"index_share_for_mtp_iteration": true,
	"index_topk": 2048,
	"indexer_rope_interleave": true,
	"indexer_types": [
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full"
	],
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"kv_lora_rank": 512,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"deepseek_sparse_attention",
	"linear_attention"
	],
	"linear_attn_config": {
	"full_attn_layers": [
	3,
	7,
	11,
	15,
	19,
	23,
	27,
	31,
	35,
	39,
	43
	],
	"gate_lower_bound": -5.0,
	"head_dim": 128,
	"kda_layers": [
	0,
	1,
	2,
	4,
	5,
	6,
	8,
	9,
	10,
	12,
	13,
	14,
	16,
	17,
	18,
	20,
	21,
	22,
	24,
	25,
	26,
	28,
	29,
	30,
	32,
	33,
	34,
	36,
	37,
	38,
	40,
	41,
	42,
	44
	],
	"num_heads": 64,
	"short_conv_kernel_size": 4
	},
	"linear_conv_kernel_dim": 4,
	"linear_head_dim": 128,
	"linear_lower_bound": -5.0,
	"linear_num_heads": 64,
	"max_position_embeddings": 1048576,
	"mhc": true,
	"mla_use_nope": true,
	"mlp_layer_types": [
	"dense",
	"dense",
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"model_type": "glm5_next_text",
	"moe_intermediate_size": 2048,
	"moe_router_dtype": "float32",
	"n_group": 1,
	"n_routed_experts": 288,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 64,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 45,
	"num_key_value_heads": 64,
	"num_nextn_predict_layers": 1,
	"output_router_logits": false,
	"pad_token_id": 154820,
	"q_lora_rank": 1536,
	"qk_head_dim": 256,
	"qk_nope_head_dim": 256,
	"qk_rope_head_dim": 0,
	"rms_norm_eps": 1e-05,
	"routed_scaling_factor": 2.5,
	"router_aux_loss_coef": 0.001,
	"scoring_func": "sigmoid",
	"swiglu_limit": 10.0,
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "noaux_tc",
	"use_cache": true,
	"v_head_dim": 256,
	"vocab_size": 154880
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.16.1",
	"video_end_token_id": 154833,
	"video_start_token_id": 154832,
	"video_token_id": 154855,
	"vision_config": {
	"attention_bias": true,
	"attention_dropout": 0.0,
	"depth": 24,
	"dtype": "bfloat16",
	"hidden_act": "silu",
	"hidden_size": 1024,
	"image_size": 448,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"model_type": "glm5_next_vision",
	"num_heads": 16,
	"out_hidden_size": 4096,
	"patch_size": 14,
	"projection_intermediate_size": 10240,
	"rms_norm_eps": 1e-05,
	"spatial_merge_size": 2,
	"swiglu_limit": 10.0,
	"temporal_patch_size": 2
	}
	}