Instructions to use thoddnn/Qwen3-VL-2B-Instruct-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thoddnn/Qwen3-VL-2B-Instruct-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="thoddnn/Qwen3-VL-2B-Instruct-4bit")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("thoddnn/Qwen3-VL-2B-Instruct-4bit")
model = AutoModelForImageTextToText.from_pretrained("thoddnn/Qwen3-VL-2B-Instruct-4bit")
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]:]))

MLX

How to use thoddnn/Qwen3-VL-2B-Instruct-4bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("thoddnn/Qwen3-VL-2B-Instruct-4bit")
config = load_config("thoddnn/Qwen3-VL-2B-Instruct-4bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use thoddnn/Qwen3-VL-2B-Instruct-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thoddnn/Qwen3-VL-2B-Instruct-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": "thoddnn/Qwen3-VL-2B-Instruct-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/thoddnn/Qwen3-VL-2B-Instruct-4bit

SGLang

How to use thoddnn/Qwen3-VL-2B-Instruct-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 "thoddnn/Qwen3-VL-2B-Instruct-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": "thoddnn/Qwen3-VL-2B-Instruct-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 "thoddnn/Qwen3-VL-2B-Instruct-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": "thoddnn/Qwen3-VL-2B-Instruct-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"
						}
					}
				]
			}
		]
	}'

Pi new

How to use thoddnn/Qwen3-VL-2B-Instruct-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "thoddnn/Qwen3-VL-2B-Instruct-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "thoddnn/Qwen3-VL-2B-Instruct-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use thoddnn/Qwen3-VL-2B-Instruct-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "thoddnn/Qwen3-VL-2B-Instruct-4bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default thoddnn/Qwen3-VL-2B-Instruct-4bit

Run Hermes

hermes

Docker Model Runner
How to use thoddnn/Qwen3-VL-2B-Instruct-4bit with Docker Model Runner:
```
docker model run hf.co/thoddnn/Qwen3-VL-2B-Instruct-4bit
```

Qwen3-VL-2B-Instruct-4bit / config.json

thoddnn

Duplicate from mlx-community/Qwen3-VL-2B-Instruct-4bit

a067b09 verified 4 months ago

raw

history blame contribute delete

7.14 kB

	{
	"add_cross_attention": false,
	"architectures": [
	"Qwen3VLForConditionalGeneration"
	],
	"bad_words_ids": null,
	"begin_suppress_tokens": null,
	"bos_token_id": null,
	"chunk_size_feed_forward": 0,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"diversity_penalty": 0.0,
	"do_sample": false,
	"dtype": null,
	"early_stopping": false,
	"encoder_no_repeat_ngram_size": 0,
	"eos_token_id": null,
	"exponential_decay_length_penalty": null,
	"finetuning_task": null,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"image_token_id": 151655,
	"is_decoder": false,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"length_penalty": 1.0,
	"max_length": 20,
	"min_length": 0,
	"model_type": "qwen3_vl",
	"no_repeat_ngram_size": 0,
	"num_beam_groups": 1,
	"num_beams": 1,
	"num_return_sequences": 1,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_scores": false,
	"pad_token_id": null,
	"prefix": null,
	"problem_type": null,
	"pruned_heads": {},
	"quantization": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"remove_invalid_values": false,
	"repetition_penalty": 1.0,
	"return_dict": true,
	"return_dict_in_generate": false,
	"sep_token_id": null,
	"suppress_tokens": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"text_config": {
	"vocab_size": 151936,
	"max_position_embeddings": 262144,
	"hidden_size": 2048,
	"intermediate_size": 6144,
	"num_hidden_layers": 28,
	"num_attention_heads": 16,
	"num_key_value_heads": 8,
	"head_dim": 128,
	"hidden_act": "silu",
	"initializer_range": 0.02,
	"rms_norm_eps": 1e-06,
	"use_cache": true,
	"rope_theta": 5000000,
	"rope_scaling": {
	"mrope_interleaved": true,
	"mrope_section": [
	24,
	20,
	20
	],
	"rope_type": "default"
	},
	"attention_bias": false,
	"attention_dropout": 0.0,
	"return_dict": true,
	"output_hidden_states": false,
	"torchscript": false,
	"dtype": "bfloat16",
	"pruned_heads": {},
	"tie_word_embeddings": true,
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"is_decoder": false,
	"cross_attention_hidden_size": null,
	"add_cross_attention": false,
	"tie_encoder_decoder": false,
	"architectures": null,
	"finetuning_task": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"task_specific_params": null,
	"problem_type": null,
	"tokenizer_class": null,
	"prefix": null,
	"bos_token_id": 151643,
	"pad_token_id": null,
	"eos_token_id": 151645,
	"sep_token_id": null,
	"decoder_start_token_id": null,
	"max_length": 20,
	"min_length": 0,
	"do_sample": false,
	"early_stopping": false,
	"num_beams": 1,
	"temperature": 1.0,
	"top_k": 50,
	"top_p": 1.0,
	"typical_p": 1.0,
	"repetition_penalty": 1.0,
	"length_penalty": 1.0,
	"no_repeat_ngram_size": 0,
	"encoder_no_repeat_ngram_size": 0,
	"bad_words_ids": null,
	"num_return_sequences": 1,
	"output_scores": false,
	"return_dict_in_generate": false,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"remove_invalid_values": false,
	"exponential_decay_length_penalty": null,
	"suppress_tokens": null,
	"begin_suppress_tokens": null,
	"num_beam_groups": 1,
	"diversity_penalty": 0.0,
	"_name_or_path": "",
	"model_type": "qwen3_vl_text",
	"tf_legacy_loss": false,
	"use_bfloat16": false,
	"output_attentions": false
	},
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torchscript": false,
	"transformers_version": "4.57.1",
	"typical_p": 1.0,
	"use_bfloat16": false,
	"video_token_id": 151656,
	"vision_config": {
	"return_dict": true,
	"output_hidden_states": false,
	"torchscript": false,
	"dtype": null,
	"pruned_heads": {},
	"tie_word_embeddings": true,
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"is_decoder": false,
	"cross_attention_hidden_size": null,
	"add_cross_attention": false,
	"tie_encoder_decoder": false,
	"architectures": null,
	"finetuning_task": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"task_specific_params": null,
	"problem_type": null,
	"tokenizer_class": null,
	"prefix": null,
	"bos_token_id": null,
	"pad_token_id": null,
	"eos_token_id": null,
	"sep_token_id": null,
	"decoder_start_token_id": null,
	"max_length": 20,
	"min_length": 0,
	"do_sample": false,
	"early_stopping": false,
	"num_beams": 1,
	"temperature": 1.0,
	"top_k": 50,
	"top_p": 1.0,
	"typical_p": 1.0,
	"repetition_penalty": 1.0,
	"length_penalty": 1.0,
	"no_repeat_ngram_size": 0,
	"encoder_no_repeat_ngram_size": 0,
	"bad_words_ids": null,
	"num_return_sequences": 1,
	"output_scores": false,
	"return_dict_in_generate": false,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"remove_invalid_values": false,
	"exponential_decay_length_penalty": null,
	"suppress_tokens": null,
	"begin_suppress_tokens": null,
	"num_beam_groups": 1,
	"diversity_penalty": 0.0,
	"_name_or_path": "",
	"model_type": "qwen3_vl",
	"tf_legacy_loss": false,
	"use_bfloat16": false,
	"depth": 24,
	"hidden_size": 1024,
	"hidden_act": "gelu_pytorch_tanh",
	"intermediate_size": 4096,
	"num_heads": 16,
	"in_channels": 3,
	"patch_size": 16,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2,
	"out_hidden_size": 2048,
	"num_position_embeddings": 2304,
	"initializer_range": 0.02,
	"deepstack_visual_indexes": [
	5,
	11,
	17
	],
	"output_attentions": false
	},
	"vision_end_token_id": 151653,
	"vision_start_token_id": 151652
	}