Instructions to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="second-state/Qwen2.5-VL-32B-Instruct-GGUF")
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("second-state/Qwen2.5-VL-32B-Instruct-GGUF")
model = AutoModelForMultimodalLM.from_pretrained("second-state/Qwen2.5-VL-32B-Instruct-GGUF")

llama-cpp-python

How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/Qwen2.5-VL-32B-Instruct-GGUF",
	filename="Qwen2.5-VL-32B-Instruct-Q2_K.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/Qwen2.5-VL-32B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Qwen2.5-VL-32B-Instruct-GGUF",
		"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/second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M

SGLang

How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF 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 "second-state/Qwen2.5-VL-32B-Instruct-GGUF" \
    --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": "second-state/Qwen2.5-VL-32B-Instruct-GGUF",
		"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 "second-state/Qwen2.5-VL-32B-Instruct-GGUF" \
        --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": "second-state/Qwen2.5-VL-32B-Instruct-GGUF",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with Ollama:
```
ollama run hf.co/second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for second-state/Qwen2.5-VL-32B-Instruct-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for second-state/Qwen2.5-VL-32B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/Qwen2.5-VL-32B-Instruct-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use second-state/Qwen2.5-VL-32B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/Qwen2.5-VL-32B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-VL-32B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

apepkuss79 commited on Apr 28, 2025

Commit

2736df0

verified ·

1 Parent(s): 4befc88

Update models

Browse files

Files changed (18) hide show

.gitattributes +16 -0
Qwen2.5-VL-32B-Instruct-Q2_K.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q3_K_L.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q3_K_M.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q3_K_S.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q4_0.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q4_K_M.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q4_K_S.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q5_0.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q5_K_M.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q5_K_S.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q6_K.gguf +3 -0
Qwen2.5-VL-32B-Instruct-Q8_0.gguf +3 -0
Qwen2.5-VL-32B-Instruct-f16-00001-of-00003.gguf +3 -0
Qwen2.5-VL-32B-Instruct-f16-00002-of-00003.gguf +3 -0
Qwen2.5-VL-32B-Instruct-f16-00003-of-00003.gguf +3 -0
Qwen2.5-VL-32B-Instruct-vision.gguf +3 -0
config.json +51 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-f16-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-f16-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-f16-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-32B-Instruct-vision.gguf filter=lfs diff=lfs merge=lfs -text

Qwen2.5-VL-32B-Instruct-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c61b829a91f940857d9122b41da53c5766f36e1ac0efaf21760ff15241931d79
+size 12313097088

Qwen2.5-VL-32B-Instruct-Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7cc15891f0abdb10f23f1a1fef6df670eea90cf378f5b366d9d6b72ef085af
+size 17247077248

Qwen2.5-VL-32B-Instruct-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bdce1eb5b62850be13a2aeb67c89d916224429df67e86047b734cfaba60da785
+size 15935046528

Qwen2.5-VL-32B-Instruct-Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd1e3f81ef40ed944b602bf6275bba89d97496284a37b42f0ff27c131c6c72c
+size 14392329088

Qwen2.5-VL-32B-Instruct-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c80f3dd9f7840e01ceddb757b9ba67289a2890e0dd833cdb369afc0d6820ad2
+size 18640229248

Qwen2.5-VL-32B-Instruct-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:61cc63cd2402bd42a146bd37a439dd6563feb3bc97c56c136293236e80a25fe9
+size 19851334528

Qwen2.5-VL-32B-Instruct-Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd1a1a2c6ef220f3bff28dfd2126095d43629d25991efc7cccb88935fa5d6d0
+size 18784408448

Qwen2.5-VL-32B-Instruct-Q5_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:596bdd16db6ae83abaf77a8207aad3f69e3fe66c08171f74ceaab0aaba68cc8c
+size 22638252928

Qwen2.5-VL-32B-Instruct-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:44007e389423226293f3951e16f74df292918c6ddc9be6de8a7696cb6c72a02c
+size 23262155648

Qwen2.5-VL-32B-Instruct-Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5215728241cb5d83b219aeaaa081c313400c470001da7c96f0d8928c72a751
+size 22638252928

Qwen2.5-VL-32B-Instruct-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:557e23e8a65fefd34541d9cb765e2a565f4c1d15dc0e2dc94aa3008b1dbf03e5
+size 26886153088

Qwen2.5-VL-32B-Instruct-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:71b0d85a72edc68d4cd0e8737a4876f03b9e24e1dfa9ece4b3b3c8879af206d5
+size 34820883328

Qwen2.5-VL-32B-Instruct-f16-00001-of-00003.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:213fc02ec03b8bc5437b49569d0c084f2fa17f65d82ced5c537533bda2929915
+size 29845222784

Qwen2.5-VL-32B-Instruct-f16-00002-of-00003.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5de4c4692104a1c8e3bde1123d600631b06ef66a5ff5ac990e6a897c8cd836d
+size 29823611296

Qwen2.5-VL-32B-Instruct-f16-00003-of-00003.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5dedf73adaa7a1787e2bd7927b0000e57f560e6f1188053fc0c5760b9aae7e
+size 5867134368

Qwen2.5-VL-32B-Instruct-vision.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91f491cdee19d1971400bde2f983db1887bd7d445b57629c7146c6aad17030ad
+size 1378753664

config.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 64,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "intermediate_size": 3456,
+    "model_type": "qwen2_5_vl",
+    "out_hidden_size": 5120,
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}