Downloads · 30 days
0
SmolVLM2-2.2B-Instruct-ternary
AsadIsmail/SmolVLM2-2.2B-Instruct-ternary
SmolVLM2-2.2B-Instruct-ternary is a image-text-to-text model from AsadIsmail. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Ternary-quantized version of HuggingFaceTB/SmolVLM2-2.2B-Instruct using ternary-quant.
Access
Public
Updated Apr 15, 2026
Repo size
1.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.npz1.8 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Apr 14, 2026
- Updated
- Apr 15, 2026
- SHA
- 8ae73d48
Try a prompt
Base models
Model card
From the Hugging Face model README
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))
Collection
Part of ternary-models.
GitHub: github.com/Asad-Ismail/ternary-models | Library: github.com/Asad-Ismail/ternary-quant
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Languages
- en
- Created
- Apr 14, 2026
- Updated
- Apr 15, 2026