HuggingFaceTB / image-text-to-text updated 1 year ago

SmolVLM-256M-Instruct

Name: SmolVLM-256M-Instruct
Author: HuggingFaceTB

SmolVLM-256M is the smallest multimodal model in the world. It accepts arbitrary sequences of image and text inputs to produce text outputs. It's designed for efficiency. SmolVLM can answer questions about images, describe visual content, or transcribe text. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on one i...

Params

260 M

Context

—

Downloads 30d

1.1 M

Likes

395

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.1 M1.0 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	0.5 GB	1.1 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Idefics3ForConditionalGeneration
Parameters: 260 M
Tensor type: BF16
Vocabulary: 49,280
Licence: apache-2.0
First seen on the Hub: 2025-01-17
Base model: SmolLM2-135M-Instruct
Training datasets: HuggingFaceM4/the_cauldron, HuggingFaceM4/Docmatix
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base SmolLM2-135M-Instruct HuggingFaceTB 2.0 M

Compare with

Qwen3.5-9B 12.4 M gemma-4-31B-it 11.9 M gemma-4-26B-A4B-it 11.7 M Qwen2.5-VL-7B-Instruct 9.3 M Qwen3.6-35B-A3B-FP8 8.9 M Qwen3.6-27B-FP8 7.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB