LFM3-VL-2B is a vision-language model for on-device visual understanding. It takes text, images, and video as input, and combines the LFM3 language model with a new in-house vision encoder.
Alternatives to LFM3-VL-2B
120 open-weight models that do the same job as LFM3-VL-2B (1.9B vision), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
NV-Reason-CT is a 3D vision-language model (VLM) for CT image analysis. It combines a native 3D vision encoder (3D ViT) with a language model and is designed for radiology report generation, general question answering, and multi-step reasoning across chest and abdominal CT volumes.
5.3B256K ctx Custom licence3.9K 97Sept 2026- Same category
- Larger (5.3B vs 1.9B)
- Commercial use OK
BLIP-2 model, leveraging OPT-2.7b (a large language model with 2.7 billion parameters). It was introduced in the paper BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models by Li et al. and first released in this repository.
3.7BMIT379.4K 448Feb 2023- Same category
- Similar size (3.7B vs 1.9B)
- Commercial use OK
Molmo2-ER (Embodied Reasoning) is a 4B vision–language model specialized for the embodied perception skills that downstream action models depend on: scene understanding, pixel-accurate pointing, multi-image and egocentric–exocentric correspondence, and video temporal reasoning.
4.9B16K ctx Apache 2.03.5K 17May 2026- Same category
- Larger (4.9B vs 1.9B)
- Commercial use OK
DeskForge-Qwen3.5-4B is Qwen3.5-4B fine-tuned for desktop GUI grounding and next-action prediction using grounding and GUI-workflow supervision.
4.5B256K ctx Apache 2.0623 9Sept 2026- Same category
- Larger (4.5B vs 1.9B)
- Commercial use OK
TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.
5B128K ctx Gemma Terms of Use10.5K 921Jan 2026- Same category
- Larger (5B vs 1.9B)
Model family: GroundAnything — DLM / parallel decoding · GroundAnything-VLM — autoregressive.
4.8B256K ctx apache-2.0-with-upstream-kimi-k31.2K 69Sept 2026- Same category
- Larger (4.8B vs 1.9B)
- Commercial use OK
FastVLM was introduced in FastVLM: Efficient Vision Encoding for Vision Language Models. (CVPR 2025)
759M32K ctx Apple Machine Learning Research License22.4K 410Aug 2025- Same category
- Smaller (759M vs 1.9B)
Transformers PaliGemma 2 3B weights fine-tuned on a mixture of academic tasks using 448x448 input images. PaliGemma 2 mix checkpoints are fine-tuned on a diverse set of tasks and are ready to use out of the box while pt checkpoints are pre-trained and intended for further fine-tuning.
3BGemma Terms of Use2.4K 72Nov 2024- Same category
- Similar size (3B vs 1.9B)
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control.
4.8B256K ctx apache-2.0-with-upstream-kimi-k3956 44Sept 2026- Same category
- Larger (4.8B vs 1.9B)
- Commercial use OK
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.
4.7B40K ctx Apache 2.016.2K 30Aug 2025- Same category
- Larger (4.7B vs 1.9B)
- Commercial use OK
Kosmos-2.5 is a multimodal literate model for machine reading of text-intensive images. Pre-trained on large-scale text-intensive images, Kosmos-2.5 excels in two distinct yet cooperative transcription tasks: (1) generating spatially-aware text blocks, where each block of text is assigned its…
1.4BMIT2.7K 277May 2024- Same category
- Similar size (1.4B vs 1.9B)
- Commercial use OK
HyperCLOVAX-SEED-Vision-Instruct-3B is a model developed by NAVER, built upon its proprietary backbone model and fine-tuned through post-training. It is capable of understanding both text and images, as well as generating text.
3.7B128K ctx hyperclovax-seed2.9K 221Apr 2025- Same category
- Similar size (3.7B vs 1.9B)
Important Update! We made a few small but important updates to this HF/transformers-compatible checkpoint to ensure exact outputs to our native model checkpoint on March 29, 2026 ~6PM PST. If you downloaded this model checkpoint earlier than this time, we recommend re-downloading it.
4.9B10K ctx Apache 2.02.4K 36Mar 2026- Same category
- Larger (4.9B vs 1.9B)
- Commercial use OK
Transformers PaliGemma 2 3B weights, pre-trained with 896*896 input images and 512 token input/output text sequences. The model is available in the bfloat16 format for fine-tuning.
3BGemma Terms of Use1.4K 29Nov 2024- Same category
- Similar size (3B vs 1.9B)
This model is part of the GELab-Zero project, which presents the Step-GUI Technical Report [Paper] [Project Page] [Code].
4.4B256K ctx Apache 2.02.3K 153Nov 2025- Same category
- Larger (4.4B vs 1.9B)
- Commercial use OK
UForm-Gen2-dpo is a small generative vision-language model alined for Image Captioning and Visual Question Answering on preference datasets VLFeedback and LLaVA-Human-Preference-10K using Direct Preference Optimization (DPO).
1.3BApache 2.05K 46Mar 2024- Same category
- Similar size (1.3B vs 1.9B)
- Commercial use OK
ShieldGemma 2 is a model trained on Gemma 3's 4B IT checkpoint for image safety classification across key categories that takes in images and outputs safety labels per policy.
4.3B8K ctx Gemma Terms of Use12K 192Mar 2025- Same category
- Larger (4.3B vs 1.9B)
In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.
8.3B125K ctx Apache 2.05.2M 1.8KJan 2025- Same category
- Larger (8.3B vs 1.9B)
- Commercial use OK
- Widely used
ZwZ-4B is a fine-grained multimodal perception model built upon Qwen3-VL-4B. It is trained using Region-to-Image Distillation (R2I) combined with reinforcement learning, enabling superior fine-grained visual understanding in a single forward pass — no inference-time zooming or tool calling…
4.8B256K ctx Apache 2.01.6K 34Feb 2026- Same category
- Larger (4.8B vs 1.9B)
- Commercial use OK
The H2OVL-Mississippi-800M is a compact yet powerful vision-language model from H2O.ai, featuring 0.8 billion parameters. Despite its small size, it delivers state-of-the-art performance in text recognition, excelling in the Text Recognition segment of OCRBench and outperforming much larger models…
826M8K ctx Apache 2.027.3K 43Oct 2024- Same category
- Smaller (826M vs 1.9B)
- Commercial use OK
MiniCPM-V 2.8B is a strong multimodal large language model for efficient end-side deployment. The model is built based on SigLip-400M and MiniCPM-2.4B, connected by a perceiver resampler. Our latest version, MiniCPM-V 2.0 has several notable features.
3.4B4K ctx Unknown licence10.1K 507Apr 2024- Same category
- Similar size (3.4B vs 1.9B)
Transformers PaliGemma 3B weights, pre-trained with 448*448 input images and 512 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.
2.9BGemma Terms of Use1.7K 35May 2024- Same category
- Similar size (2.9B vs 1.9B)
The Phi-3-Vision-128K-Instruct is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.
4.1B128K ctx MIT38.2K 979May 2024- Same category
- Larger (4.1B vs 1.9B)
- Commercial use OK
Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels. It achieves comparable performance to SOTA MLLMs Qwen2-VL and InternVL2.5 on question-answering benchmarks.
1.2B32K ctx Apache 2.0498 31Jan 2025- Same category
- Similar size (1.2B vs 1.9B)
- Commercial use OK