Instructions to use cyankiwi/InternVL3_5-8B-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyankiwi/InternVL3_5-8B-AWQ-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="cyankiwi/InternVL3_5-8B-AWQ-4bit", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("cyankiwi/InternVL3_5-8B-AWQ-4bit", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cyankiwi/InternVL3_5-8B-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyankiwi/InternVL3_5-8B-AWQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyankiwi/InternVL3_5-8B-AWQ-4bit",
		"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/cyankiwi/InternVL3_5-8B-AWQ-4bit

SGLang

How to use cyankiwi/InternVL3_5-8B-AWQ-4bit 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 "cyankiwi/InternVL3_5-8B-AWQ-4bit" \
    --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": "cyankiwi/InternVL3_5-8B-AWQ-4bit",
		"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 "cyankiwi/InternVL3_5-8B-AWQ-4bit" \
        --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": "cyankiwi/InternVL3_5-8B-AWQ-4bit",
		"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 cyankiwi/InternVL3_5-8B-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/cyankiwi/InternVL3_5-8B-AWQ-4bit
```

InternVL3_5-8B-AWQ-4bit / config.json

cpatonn

Squash history of main

baa1f86 2 months ago

Raw History Blame Contribute Delete

8.95 kB

	{
	"architectures": [
	"InternVLChatModel"
	],
	"auto_map": {
	"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
	"AutoModel": "modeling_internvl_chat.InternVLChatModel",
	"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
	},
	"downsample_ratio": 0.5,
	"dtype": "bfloat16",
	"dynamic_image_size": true,
	"eos_token_id": 151645,
	"force_image_size": 448,
	"llm_config": {
	"_name_or_path": "/root/codespace/checkpoints/Qwen3-8B",
	"architectures": [
	"Qwen3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 151643,
	"debug": false,
	"dtype": "bfloat16",
	"eos_token_id": 151645,
	"ep_size": 1,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 40960,
	"max_window_layers": 36,
	"micro_forward": false,
	"model_type": "qwen3",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000000,
	"skip_checkpoint": false,
	"sliding_window": null,
	"use_cache": false,
	"use_deepep": false,
	"use_sliding_window": false,
	"vocab_size": 151936
	},
	"max_dynamic_patch": 12,
	"min_dynamic_patch": 1,
	"model_type": "internvl_chat",
	"output_attentions": false,
	"pad2square": false,
	"pad_token_id": 151643,
	"ps_version": "v2",
	"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": 32,
	"num_bits": 4,
	"observer": "mse",
	"observer_kwargs": {},
	"strategy": "group",
	"symmetric": true,
	"type": "int"
	}
	}
	},
	"format": "pack-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"vision_model.encoder.layers.0.attn.qkv",
	"vision_model.encoder.layers.0.attn.proj",
	"vision_model.encoder.layers.0.mlp.fc1",
	"vision_model.encoder.layers.0.mlp.fc2",
	"vision_model.encoder.layers.1.attn.qkv",
	"vision_model.encoder.layers.1.attn.proj",
	"vision_model.encoder.layers.1.mlp.fc1",
	"vision_model.encoder.layers.1.mlp.fc2",
	"vision_model.encoder.layers.2.attn.qkv",
	"vision_model.encoder.layers.2.attn.proj",
	"vision_model.encoder.layers.2.mlp.fc1",
	"vision_model.encoder.layers.2.mlp.fc2",
	"vision_model.encoder.layers.3.attn.qkv",
	"vision_model.encoder.layers.3.attn.proj",
	"vision_model.encoder.layers.3.mlp.fc1",
	"vision_model.encoder.layers.3.mlp.fc2",
	"vision_model.encoder.layers.4.attn.qkv",
	"vision_model.encoder.layers.4.attn.proj",
	"vision_model.encoder.layers.4.mlp.fc1",
	"vision_model.encoder.layers.4.mlp.fc2",
	"vision_model.encoder.layers.5.attn.qkv",
	"vision_model.encoder.layers.5.attn.proj",
	"vision_model.encoder.layers.5.mlp.fc1",
	"vision_model.encoder.layers.5.mlp.fc2",
	"vision_model.encoder.layers.6.attn.qkv",
	"vision_model.encoder.layers.6.attn.proj",
	"vision_model.encoder.layers.6.mlp.fc1",
	"vision_model.encoder.layers.6.mlp.fc2",
	"vision_model.encoder.layers.7.attn.qkv",
	"vision_model.encoder.layers.7.attn.proj",
	"vision_model.encoder.layers.7.mlp.fc1",
	"vision_model.encoder.layers.7.mlp.fc2",
	"vision_model.encoder.layers.8.attn.qkv",
	"vision_model.encoder.layers.8.attn.proj",
	"vision_model.encoder.layers.8.mlp.fc1",
	"vision_model.encoder.layers.8.mlp.fc2",
	"vision_model.encoder.layers.9.attn.qkv",
	"vision_model.encoder.layers.9.attn.proj",
	"vision_model.encoder.layers.9.mlp.fc1",
	"vision_model.encoder.layers.9.mlp.fc2",
	"vision_model.encoder.layers.10.attn.qkv",
	"vision_model.encoder.layers.10.attn.proj",
	"vision_model.encoder.layers.10.mlp.fc1",
	"vision_model.encoder.layers.10.mlp.fc2",
	"vision_model.encoder.layers.11.attn.qkv",
	"vision_model.encoder.layers.11.attn.proj",
	"vision_model.encoder.layers.11.mlp.fc1",
	"vision_model.encoder.layers.11.mlp.fc2",
	"vision_model.encoder.layers.12.attn.qkv",
	"vision_model.encoder.layers.12.attn.proj",
	"vision_model.encoder.layers.12.mlp.fc1",
	"vision_model.encoder.layers.12.mlp.fc2",
	"vision_model.encoder.layers.13.attn.qkv",
	"vision_model.encoder.layers.13.attn.proj",
	"vision_model.encoder.layers.13.mlp.fc1",
	"vision_model.encoder.layers.13.mlp.fc2",
	"vision_model.encoder.layers.14.attn.qkv",
	"vision_model.encoder.layers.14.attn.proj",
	"vision_model.encoder.layers.14.mlp.fc1",
	"vision_model.encoder.layers.14.mlp.fc2",
	"vision_model.encoder.layers.15.attn.qkv",
	"vision_model.encoder.layers.15.attn.proj",
	"vision_model.encoder.layers.15.mlp.fc1",
	"vision_model.encoder.layers.15.mlp.fc2",
	"vision_model.encoder.layers.16.attn.qkv",
	"vision_model.encoder.layers.16.attn.proj",
	"vision_model.encoder.layers.16.mlp.fc1",
	"vision_model.encoder.layers.16.mlp.fc2",
	"vision_model.encoder.layers.17.attn.qkv",
	"vision_model.encoder.layers.17.attn.proj",
	"vision_model.encoder.layers.17.mlp.fc1",
	"vision_model.encoder.layers.17.mlp.fc2",
	"vision_model.encoder.layers.18.attn.qkv",
	"vision_model.encoder.layers.18.attn.proj",
	"vision_model.encoder.layers.18.mlp.fc1",
	"vision_model.encoder.layers.18.mlp.fc2",
	"vision_model.encoder.layers.19.attn.qkv",
	"vision_model.encoder.layers.19.attn.proj",
	"vision_model.encoder.layers.19.mlp.fc1",
	"vision_model.encoder.layers.19.mlp.fc2",
	"vision_model.encoder.layers.20.attn.qkv",
	"vision_model.encoder.layers.20.attn.proj",
	"vision_model.encoder.layers.20.mlp.fc1",
	"vision_model.encoder.layers.20.mlp.fc2",
	"vision_model.encoder.layers.21.attn.qkv",
	"vision_model.encoder.layers.21.attn.proj",
	"vision_model.encoder.layers.21.mlp.fc1",
	"vision_model.encoder.layers.21.mlp.fc2",
	"vision_model.encoder.layers.22.attn.qkv",
	"vision_model.encoder.layers.22.attn.proj",
	"vision_model.encoder.layers.22.mlp.fc1",
	"vision_model.encoder.layers.22.mlp.fc2",
	"vision_model.encoder.layers.23.attn.qkv",
	"vision_model.encoder.layers.23.attn.proj",
	"vision_model.encoder.layers.23.mlp.fc1",
	"vision_model.encoder.layers.23.mlp.fc2",
	"language_model.lm_head",
	"mlp1.1",
	"mlp1.3"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.11.1.a20250828"
	},
	"select_layer": -1,
	"template": "internvl2_5",
	"tie_word_embeddings": false,
	"transformers_version": null,
	"use_backbone_lora": 0,
	"use_llm_lora": 0,
	"use_thumbnail": true,
	"vision_config": {
	"architectures": [
	"InternVisionModel"
	],
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_intern_vit.InternVisionConfig",
	"AutoModel": "modeling_intern_vit.InternVisionModel"
	},
	"drop_path_rate": 0.1,
	"dropout": 0.0,
	"dtype": "bfloat16",
	"hidden_act": "gelu",
	"hidden_size": 1024,
	"image_size": 448,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"layer_norm_eps": 1e-06,
	"model_type": "intern_vit_6b",
	"norm_type": "layer_norm",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"patch_size": 14,
	"qk_normalization": false,
	"qkv_bias": true,
	"use_fa3": false,
	"use_flash_attn": false
	}
	}