Instructions to use EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16 with Transformers:

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

pipe = pipeline("text-generation", model="EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16")
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("EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16")
model = AutoModelForMultimodalLM.from_pretrained("EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16")
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 EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16

SGLang

How to use EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16 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 "EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16" \
    --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": "EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16",
		"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 "EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16" \
        --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": "EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16 with Docker Model Runner:
```
docker model run hf.co/EmbeddedLLM/Qwen3-VL-30B-A3B-Instruct.w4a16
```

Qwen3-VL-30B-A3B-Instruct.w4a16 / config.json

tjellm

Add files using upload-large-folder tool

2d18998 verified 5 months ago

raw

history blame contribute delete

10.1 kB

	{
	"architectures": [
	"Qwen3VLMoeForConditionalGeneration"
	],
	"dtype": "bfloat16",
	"image_token_id": 151655,
	"model_type": "qwen3_vl_moe",
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "pack-quantized",
	"input_activations": null,
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": 128,
	"num_bits": 4,
	"observer": "minmax",
	"observer_kwargs": {},
	"strategy": "group",
	"symmetric": true,
	"type": "int"
	}
	}
	},
	"format": "pack-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"model.visual.blocks.0.attn.qkv",
	"model.visual.blocks.0.attn.proj",
	"model.visual.blocks.0.mlp.linear_fc1",
	"model.visual.blocks.0.mlp.linear_fc2",
	"model.visual.blocks.1.attn.qkv",
	"model.visual.blocks.1.attn.proj",
	"model.visual.blocks.1.mlp.linear_fc1",
	"model.visual.blocks.1.mlp.linear_fc2",
	"model.visual.blocks.2.attn.qkv",
	"model.visual.blocks.2.attn.proj",
	"model.visual.blocks.2.mlp.linear_fc1",
	"model.visual.blocks.2.mlp.linear_fc2",
	"model.visual.blocks.3.attn.qkv",
	"model.visual.blocks.3.attn.proj",
	"model.visual.blocks.3.mlp.linear_fc1",
	"model.visual.blocks.3.mlp.linear_fc2",
	"model.visual.blocks.4.attn.qkv",
	"model.visual.blocks.4.attn.proj",
	"model.visual.blocks.4.mlp.linear_fc1",
	"model.visual.blocks.4.mlp.linear_fc2",
	"model.visual.blocks.5.attn.qkv",
	"model.visual.blocks.5.attn.proj",
	"model.visual.blocks.5.mlp.linear_fc1",
	"model.visual.blocks.5.mlp.linear_fc2",
	"model.visual.blocks.6.attn.qkv",
	"model.visual.blocks.6.attn.proj",
	"model.visual.blocks.6.mlp.linear_fc1",
	"model.visual.blocks.6.mlp.linear_fc2",
	"model.visual.blocks.7.attn.qkv",
	"model.visual.blocks.7.attn.proj",
	"model.visual.blocks.7.mlp.linear_fc1",
	"model.visual.blocks.7.mlp.linear_fc2",
	"model.visual.blocks.8.attn.qkv",
	"model.visual.blocks.8.attn.proj",
	"model.visual.blocks.8.mlp.linear_fc1",
	"model.visual.blocks.8.mlp.linear_fc2",
	"model.visual.blocks.9.attn.qkv",
	"model.visual.blocks.9.attn.proj",
	"model.visual.blocks.9.mlp.linear_fc1",
	"model.visual.blocks.9.mlp.linear_fc2",
	"model.visual.blocks.10.attn.qkv",
	"model.visual.blocks.10.attn.proj",
	"model.visual.blocks.10.mlp.linear_fc1",
	"model.visual.blocks.10.mlp.linear_fc2",
	"model.visual.blocks.11.attn.qkv",
	"model.visual.blocks.11.attn.proj",
	"model.visual.blocks.11.mlp.linear_fc1",
	"model.visual.blocks.11.mlp.linear_fc2",
	"model.visual.blocks.12.attn.qkv",
	"model.visual.blocks.12.attn.proj",
	"model.visual.blocks.12.mlp.linear_fc1",
	"model.visual.blocks.12.mlp.linear_fc2",
	"model.visual.blocks.13.attn.qkv",
	"model.visual.blocks.13.attn.proj",
	"model.visual.blocks.13.mlp.linear_fc1",
	"model.visual.blocks.13.mlp.linear_fc2",
	"model.visual.blocks.14.attn.qkv",
	"model.visual.blocks.14.attn.proj",
	"model.visual.blocks.14.mlp.linear_fc1",
	"model.visual.blocks.14.mlp.linear_fc2",
	"model.visual.blocks.15.attn.qkv",
	"model.visual.blocks.15.attn.proj",
	"model.visual.blocks.15.mlp.linear_fc1",
	"model.visual.blocks.15.mlp.linear_fc2",
	"model.visual.blocks.16.attn.qkv",
	"model.visual.blocks.16.attn.proj",
	"model.visual.blocks.16.mlp.linear_fc1",
	"model.visual.blocks.16.mlp.linear_fc2",
	"model.visual.blocks.17.attn.qkv",
	"model.visual.blocks.17.attn.proj",
	"model.visual.blocks.17.mlp.linear_fc1",
	"model.visual.blocks.17.mlp.linear_fc2",
	"model.visual.blocks.18.attn.qkv",
	"model.visual.blocks.18.attn.proj",
	"model.visual.blocks.18.mlp.linear_fc1",
	"model.visual.blocks.18.mlp.linear_fc2",
	"model.visual.blocks.19.attn.qkv",
	"model.visual.blocks.19.attn.proj",
	"model.visual.blocks.19.mlp.linear_fc1",
	"model.visual.blocks.19.mlp.linear_fc2",
	"model.visual.blocks.20.attn.qkv",
	"model.visual.blocks.20.attn.proj",
	"model.visual.blocks.20.mlp.linear_fc1",
	"model.visual.blocks.20.mlp.linear_fc2",
	"model.visual.blocks.21.attn.qkv",
	"model.visual.blocks.21.attn.proj",
	"model.visual.blocks.21.mlp.linear_fc1",
	"model.visual.blocks.21.mlp.linear_fc2",
	"model.visual.blocks.22.attn.qkv",
	"model.visual.blocks.22.attn.proj",
	"model.visual.blocks.22.mlp.linear_fc1",
	"model.visual.blocks.22.mlp.linear_fc2",
	"model.visual.blocks.23.attn.qkv",
	"model.visual.blocks.23.attn.proj",
	"model.visual.blocks.23.mlp.linear_fc1",
	"model.visual.blocks.23.mlp.linear_fc2",
	"model.visual.blocks.24.attn.qkv",
	"model.visual.blocks.24.attn.proj",
	"model.visual.blocks.24.mlp.linear_fc1",
	"model.visual.blocks.24.mlp.linear_fc2",
	"model.visual.blocks.25.attn.qkv",
	"model.visual.blocks.25.attn.proj",
	"model.visual.blocks.25.mlp.linear_fc1",
	"model.visual.blocks.25.mlp.linear_fc2",
	"model.visual.blocks.26.attn.qkv",
	"model.visual.blocks.26.attn.proj",
	"model.visual.blocks.26.mlp.linear_fc1",
	"model.visual.blocks.26.mlp.linear_fc2",
	"model.visual.merger.linear_fc1",
	"model.visual.merger.linear_fc2",
	"model.visual.deepstack_merger_list.0.linear_fc1",
	"model.visual.deepstack_merger_list.0.linear_fc2",
	"model.visual.deepstack_merger_list.1.linear_fc1",
	"model.visual.deepstack_merger_list.1.linear_fc2",
	"model.visual.deepstack_merger_list.2.linear_fc1",
	"model.visual.deepstack_merger_list.2.linear_fc2",
	"model.language_model.layers.0.mlp.gate",
	"model.language_model.layers.1.mlp.gate",
	"model.language_model.layers.2.mlp.gate",
	"model.language_model.layers.3.mlp.gate",
	"model.language_model.layers.4.mlp.gate",
	"model.language_model.layers.5.mlp.gate",
	"model.language_model.layers.6.mlp.gate",
	"model.language_model.layers.7.mlp.gate",
	"model.language_model.layers.8.mlp.gate",
	"model.language_model.layers.9.mlp.gate",
	"model.language_model.layers.10.mlp.gate",
	"model.language_model.layers.11.mlp.gate",
	"model.language_model.layers.12.mlp.gate",
	"model.language_model.layers.13.mlp.gate",
	"model.language_model.layers.14.mlp.gate",
	"model.language_model.layers.15.mlp.gate",
	"model.language_model.layers.16.mlp.gate",
	"model.language_model.layers.17.mlp.gate",
	"model.language_model.layers.18.mlp.gate",
	"model.language_model.layers.19.mlp.gate",
	"model.language_model.layers.20.mlp.gate",
	"model.language_model.layers.21.mlp.gate",
	"model.language_model.layers.22.mlp.gate",
	"model.language_model.layers.23.mlp.gate",
	"model.language_model.layers.24.mlp.gate",
	"model.language_model.layers.25.mlp.gate",
	"model.language_model.layers.26.mlp.gate",
	"model.language_model.layers.27.mlp.gate",
	"model.language_model.layers.28.mlp.gate",
	"model.language_model.layers.29.mlp.gate",
	"model.language_model.layers.30.mlp.gate",
	"model.language_model.layers.31.mlp.gate",
	"model.language_model.layers.32.mlp.gate",
	"model.language_model.layers.33.mlp.gate",
	"model.language_model.layers.34.mlp.gate",
	"model.language_model.layers.35.mlp.gate",
	"model.language_model.layers.36.mlp.gate",
	"model.language_model.layers.37.mlp.gate",
	"model.language_model.layers.38.mlp.gate",
	"model.language_model.layers.39.mlp.gate",
	"model.language_model.layers.40.mlp.gate",
	"model.language_model.layers.41.mlp.gate",
	"model.language_model.layers.42.mlp.gate",
	"model.language_model.layers.43.mlp.gate",
	"model.language_model.layers.44.mlp.gate",
	"model.language_model.layers.45.mlp.gate",
	"model.language_model.layers.46.mlp.gate",
	"model.language_model.layers.47.mlp.gate",
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.13.1.a20251215"
	},
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 151643,
	"decoder_sparse_step": 1,
	"dtype": "bfloat16",
	"eos_token_id": 151645,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 6144,
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"model_type": "qwen3_vl_moe_text",
	"moe_intermediate_size": 768,
	"norm_topk_prob": true,
	"num_attention_heads": 32,
	"num_experts": 128,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 48,
	"num_key_value_heads": 4,
	"rms_norm_eps": 1e-06,
	"rope_scaling": {
	"mrope_interleaved": true,
	"mrope_section": [
	24,
	20,
	20
	],
	"rope_type": "default"
	},
	"rope_theta": 5000000,
	"router_aux_loss_coef": 0.001,
	"use_cache": true,
	"vocab_size": 151936
	},
	"tie_word_embeddings": false,
	"transformers_version": "4.57.3",
	"video_token_id": 151656,
	"vision_config": {
	"deepstack_visual_indexes": [
	8,
	16,
	24
	],
	"depth": 27,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 4304,
	"model_type": "qwen3_vl_moe",
	"num_heads": 16,
	"num_position_embeddings": 2304,
	"out_hidden_size": 2048,
	"patch_size": 16,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 151653,
	"vision_start_token_id": 151652
	}