Instructions to use AsadIsmail/SmolVLM2-2.2B-Instruct-ternary with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AsadIsmail/SmolVLM2-2.2B-Instruct-ternary with Transformers:

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

pipe = pipeline("image-text-to-text", model="AsadIsmail/SmolVLM2-2.2B-Instruct-ternary")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AsadIsmail/SmolVLM2-2.2B-Instruct-ternary", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AsadIsmail/SmolVLM2-2.2B-Instruct-ternary with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AsadIsmail/SmolVLM2-2.2B-Instruct-ternary"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AsadIsmail/SmolVLM2-2.2B-Instruct-ternary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AsadIsmail/SmolVLM2-2.2B-Instruct-ternary

SGLang

How to use AsadIsmail/SmolVLM2-2.2B-Instruct-ternary 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 "AsadIsmail/SmolVLM2-2.2B-Instruct-ternary" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AsadIsmail/SmolVLM2-2.2B-Instruct-ternary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "AsadIsmail/SmolVLM2-2.2B-Instruct-ternary" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AsadIsmail/SmolVLM2-2.2B-Instruct-ternary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AsadIsmail/SmolVLM2-2.2B-Instruct-ternary with Docker Model Runner:
```
docker model run hf.co/AsadIsmail/SmolVLM2-2.2B-Instruct-ternary
```

SmolVLM2-2.2B-Instruct — Ternary Quantized (tritplane3)

Ternary-quantized version of HuggingFaceTB/SmolVLM2-2.2B-Instruct using ternary-quant.

Compact VLM designed for edge deployment, now even smaller with ternary quantization.

Model Specifications

Property	Value
Base Model	HuggingFaceTB/SmolVLM2-2.2B-Instruct
Parameters	2.2B
Architecture	VLM (image + text)
Quantization	tritplane3 (169 layers, 10.92 effective bits)
Vision Encoder	FP16 (preserved)
Compression	1.47x
Avg Reconstruction Error	0.1236
License	Apache 2.0

Size Comparison

Method	Size	VLM Support
FP16 (original)	~4.4 GB	Yes
Ternary tritplane3	1.8 GB	Yes

No GGUF alternative exists for SmolVLM2.

Quality Verification

Validated during quantization (collapse score: 0.009 — excellent):

Test	Output
Image description (demo)	"A yellow circle with a diagonal line through it" (correct)
"What is machine learning?"	Correct, detailed explanation of ML, algorithms, training
"Explain gravity"	Accurate one-sentence explanation

Memory Requirements

Runtime	Min Memory	Hardware
`cached` (CPU)	~4 GB RAM	Any
`metal` (Apple Silicon)	~3 GB unified	M1+
`cached` (CUDA)	~3 GB VRAM	Any NVIDIA GPU

Ideal for edge deployment — runs on devices with 4 GB RAM.

Quickstart

pip install ternary-quant

from ternary_quant.inference import load_ternary_model

model, processor = load_ternary_model(
    "AsadIsmail/SmolVLM2-2.2B-Instruct-ternary",
    runtime_mode="cached", device="auto"
)

inputs = processor(text="Describe this image", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(processor.decode(outputs[0], skip_special_tokens=True))