Instructions to use second-state/SmolVLM2-256M-Video-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF")
model = AutoModelForMultimodalLM.from_pretrained("second-state/SmolVLM2-256M-Video-Instruct-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M

SGLang

How to use second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF with Ollama:
```
ollama run hf.co/second-state/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use second-state/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-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/SmolVLM2-256M-Video-Instruct-GGUF to start chatting

Docker Model Runner
How to use second-state/SmolVLM2-256M-Video-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use second-state/SmolVLM2-256M-Video-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/SmolVLM2-256M-Video-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolVLM2-256M-Video-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

apepkuss79 commited on May 29, 2025

Commit

fdfa2c3

verified ·

1 Parent(s): 4e5f83d

Update models

Browse files

Files changed (16) hide show

.gitattributes +14 -0
SmolVLM2-256M-Video-Instruct-Q2_K.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q3_K_L.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q3_K_M.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q3_K_S.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q4_0.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q4_K_M.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q4_K_S.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q5_0.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q5_K_M.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q5_K_S.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q6_K.gguf +3 -0
SmolVLM2-256M-Video-Instruct-Q8_0.gguf +3 -0
SmolVLM2-256M-Video-Instruct-f16.gguf +3 -0
SmolVLM2-256M-Video-Instruct-mmproj-f16.gguf +3 -0
config.json +142 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,17 @@ 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
+SmolVLM2-256M-Video-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-256M-Video-Instruct-mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

SmolVLM2-256M-Video-Instruct-Q2_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:615646518d0a7c3e28c7aed93382d6f6d22cf193a075c295514586985e65ea6b
+size 104254432

SmolVLM2-256M-Video-Instruct-Q3_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e0aac34a477817f29fd6dfb454026fb459e9feb6b6783a13a8f9641bd490374b
+size 113585632

SmolVLM2-256M-Video-Instruct-Q3_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3e94cb4e7eb71214fefbc6a0af7ffaa54a67dc97b5d5be1a54b8654b523579d9
+size 109562848

SmolVLM2-256M-Video-Instruct-Q3_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbd90ce125e194c714b17ef91921b7c2be796014336bc0b10db7753636f001c
+size 104254432

SmolVLM2-256M-Video-Instruct-Q4_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:49be11ed279711dd1bcac3ca0dd989e98d1a3897bd288c0704c87598cf980b3e
+size 107779552

SmolVLM2-256M-Video-Instruct-Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e545f3bc75762a24120a3059bde9a4f21c5958d5adf48c0c96acb5549f4bb645
+size 125054944

SmolVLM2-256M-Video-Instruct-Q4_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8491fcedb11faf200ce84d58b116229aa0594424a3ed1ae06cddc6fa9d85b94c
+size 121640416

SmolVLM2-256M-Video-Instruct-Q5_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f8fad50283dae3a28339c0a373d24f4c4e965647565c6350024a6215007a3bce
+size 124598752

SmolVLM2-256M-Video-Instruct-Q5_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2426fbb67ac964d06b89e6fcccb4dff754b256e660c3ad2c656f1ba9ea886930
+size 133478368

SmolVLM2-256M-Video-Instruct-Q5_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:45eaab30e4e017ae5b952fb02a42ff7f7e2ab855750cf638e3abfc9bd55bf2b0
+size 131349472

SmolVLM2-256M-Video-Instruct-Q6_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:009293a747e97921043640bb46716c558a4b4c0c60d47e2cb9183a80ef87d6be
+size 168628192

SmolVLM2-256M-Video-Instruct-Q8_0.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:af7ce9951a2f46c4f6e5def253e5b896ca5e417010e7a9949fdc9e5175c27767
+size 175056352

SmolVLM2-256M-Video-Instruct-f16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:59068440ef6ddda7e9731fb29de5d5ab475ea3fe69ba4fc54d4ec3f7bb6d02a8
+size 327811552

SmolVLM2-256M-Video-Instruct-mmproj-f16.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1a39d2340eddb2c9bf88b6e7a2b382bd06b703019dd5597d437503eb7e086deb
+size 190033280

config.json ADDED Viewed

	@@ -0,0 +1,142 @@

+{
+  "architectures": [
+    "SmolVLMForConditionalGeneration"
+  ],
+  "image_token_id": 49190,
+  "model_type": "smolvlm",
+  "pad_token_id": 128002,
+  "scale_factor": 4,
+  "text_config": {
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "None",
+    "architectures": [
+      "VLlama3ForCausalLM"
+    ],
+    "head_dim": 64,
+    "hidden_size": 576,
+    "initializer_range": 0.041666666666666664,
+    "intermediate_size": 1536,
+    "is_llama_config": true,
+    "max_position_embeddings": 8192,
+    "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
+    "num_attention_heads": 9,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 3,
+    "pad_token_id": 2,
+    "perceiver_config": {
+      "_attn_implementation_autoset": false,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "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,
+      "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,
+      "hidden_act": "silu",
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "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": "vllama3",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_key_value_heads": 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": {},
+      "qk_layer_norms_perceiver": false,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resampler_depth": 6,
+      "resampler_head_dim": 96,
+      "resampler_n_heads": 16,
+      "resampler_n_latents": 64,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.46.0",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "pixel_shuffle_factor": 4,
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_interleaved": false,
+    "rope_theta": 100000,
+    "torch_dtype": "bfloat16",
+    "transformers.js_config": {
+      "kv_cache_dtype": {
+        "fp16": "float16",
+        "q4f16": "float16"
+      }
+    },
+    "use_resampler": false,
+    "vocab_size": 49280
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_reentrant_checkpointing": false,
+  "vision_config": {
+    "hidden_size": 768,
+    "image_size": 512,
+    "max_image_size": {
+      "longest_edge": 512
+    },
+    "model_type": "smolvlm_vision",
+    "num_attention_heads": 12,
+    "patch_size": 16,
+    "size": {
+      "longest_edge": 2048
+    },
+    "tie_word_embeddings": false,
+    "use_base_siglip": true
+  },
+  "vocab_size": 49280
+}