ON-DEVICE VLM HUB
Small vision-language models that run on-device
A vision-language model answers questions about images. The models below are small enough for laptops, phones or WebGPU browsers. Use the table to shortlist, then open a head-to-head comparison with FastVLM.
| Model | Developer | Sizes | Image | Video | Multi-image | Browser | MLX | License | Best for |
|---|---|---|---|---|---|---|---|---|---|
| FastVLM2025 | Apple | 0.5B · 1.5B · 7B | Yes | Apple AMLR | Low time-to-first-token on high-resolution images; browser and Apple Silicon | ||||
| SmolVLM22025 | Hugging Face | 256M · 500M · 2.2B | Some sizes | Apache 2.0 | Tiny models with video understanding; permissive license | ||||
| LFM2.5-VL2026 | Liquid AI | 450M · 3B | Yes | LFM Open License | Grounding, screens, documents and tool calling at the edge | ||||
| Gemma 42026 | E2B · E4B · 12B · 26B-A4B · 31B | Runtime-dependent | Gemma Terms | Broad multimodal (image, video frames, audio on E2B/E4B) and agentic use | |||||
| Gemma 3n2025 | E2B · E4B | Runtime-dependent | Gemma Terms | Phone-first models with audio input and per-layer embeddings | |||||
| Qwen3-VL2025 | Alibaba | 2B · 4B · 8B (small) | Some sizes | Apache 2.0 | Strong OCR, documents and video in small dense sizes | ||||
| Moondream2024–2025 | Moondream | 2B · 3 (9B MoE, 2B active) | Some sizes | Apache 2.0 / BSL | Pointing, detection and captioning with a tiny footprint | ||||
| MiniCPM-V2025 | OpenBMB | 4.5 (8B) | No | Apache 2.0 code · MiniCPM weights | High-resolution image and video understanding on laptops | ||||
| PaliGemma 22024 | 3B · 10B · 28B | No | Gemma Terms | Fine-tuning base for detection, segmentation and captioning |
“Browser” means a maintained WebGPU/Transformers.js or ONNX build exists for at least one size. “Runtime-dependent” models run through vendor runtimes such as MediaPipe or LiteRT rather than Transformers.js.
Facts checked on 2026-09-17 against official model cards and announcements. Report an outdated row via the site’s GitHub.
Head-to-head with FastVLM
Benchmark FastVLM on your deviceHow to choose
- Start from the task: OCR and documents favour higher input resolution; video needs a model trained on frames; grounding needs boxes in the output format.
- Then the runtime: browser demos need ONNX weights; iPhone apps need MLX or Core ML; Linux servers can use anything.
- Then the license: Apache 2.0 models are simplest to ship; Apple AMLR and Gemma terms have conditions you must read.
- Finally measure on your device—published benchmarks use different protocols and cannot be compared across vendors.