LBS-27B is an agentic vision-language model based on Qwen3.8-27b. It learns to select and inspect image regions through GUI grounding, then transfers this observation policy to general-domain visual question answering and high-resolution perception.
Alternatives to LBS-27B
120 open-weight models that do the same job as LBS-27B (27B 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.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
9.7B256K ctx Apache 2.06.2M 2.4KFeb 2026- Same category
- Smaller (9.7B vs 27B)
- Commercial use OK
- Widely used
Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world.
30.5B32K ctx Apache 2.0544 25Jul 2026- Same category
- Similar size (30.5B vs 27B)
- Commercial use OK
Capability of Qwen3.6-27B with 50% less thinking tokens on average, and over 90% less in best cases. Achieved via finetuning Qwen3.6-27B (Qwen Team, 2026) with state-of-the-art algorithms on a curated set of problems of various domains and difficulty.
27.4B256K ctx Apache 2.0179 706Jul 2026- Same category
- Similar size (27.4B vs 27B)
- Commercial use OK
This repository contains an earlier open-weight Preview checkpoint of Agnes 3.0 Flash. It is distinct from the newer production/API checkpoint listed on Artificial Analysis. The Preview release has 33B parameters and a context window of 262,144 tokens.
33.1B256K ctx Apache 2.0447 250Sept 2026- Same category
- Similar size (33.1B vs 27B)
- Commercial use OK
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
27.4BGemma Terms of Use6.3K 126Mar 2025- Same category
- Similar size (27.4B vs 27B)
Here is an example of how to use the transformers library for inference:
29.7BA3B128K ctx Apache 2.01.4K 547Nov 2025- Same category
- Similar size (29.7B vs 27B)
- Commercial use OK
We introduce Intern-S2-Mobius, a 35B foundation model built on the Mobius-v0 architecture realized by Xtuner and LMDeploy.
36B256K ctx Apache 2.01K 66Jul 2026- Same category
- Similar size (36B vs 27B)
- Commercial use OK
NVIDIA-Ising-Calibration-1 analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis question categories. NVIDIA-Ising-Calibration-1 was developed by NVIDIA as a quantum calibration vision-language model built on Qwen3.5-35B-A3B.
35BA3B256K ctx NVIDIA Open Model License2K 62Mar 2026- Same category
- Similar size (35B vs 27B)
- Commercial use OK
We introduce Intern-S2-Preview, an efficient 35B scientific multimodal foundation model. Beyond conventional parameter and data scaling, Intern-S2-Preview explores task scaling: increasing the difficulty, diversity, and coverage of scientific tasks to further unlock model capabilities.
36.1BA4.9B256K ctx Apache 2.01.6K 123May 2026- Same category
- Similar size (36.1B vs 27B)
- Commercial use OK
[Dec 1, 2024] We have released the base models (with native multimodal pre-training) for Aria (Aria-Base-8K and Aria-Base-64K) for research purposes and continue training.
25.3BA4.6B64K ctx Apache 2.019.2K 638Sept 2024- Same category
- Similar size (25.3B vs 27B)
- 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.
30.8BA3B40K ctx Apache 2.02.4K 11Aug 2025- Same category
- Similar size (30.8B vs 27B)
- Commercial use OK
WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) checkpoint in the WeMM-Video family. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.
36.2BA5B256K ctx Apache 2.0239 27Nov 2026- Same category
- Similar size (36.2B vs 27B)
- Commercial use OK
- Newer release
This repository contains the UI-Venus model from the report UI-Venus-1.5 Technical Report. UI-Venus 1.5 is a unified, end-to-end GUI Agent designed for robust real-world applications. The model family includes two dense (2B/8B) and one MoE (30B-A3B) variants to meet various downstream scenarios.
31.1BA3B256K ctx Apache 2.0339 37Feb 2026- Same category
- Similar size (31.1B vs 27B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.06.1M 1.3KOct 2025- Same category
- Smaller (8.8B vs 27B)
- Commercial use OK
- Widely used
Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL.
27.5BDeepSeek License2.3K 411Dec 2024- Same category
- Similar size (27.5B vs 27B)
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
29.4BA3B128K ctx Apache 2.0720 42Jun 2025- Same category
- Similar size (29.4B vs 27B)
- 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.
38.4B40K ctx Apache 2.04.3K 47Aug 2025- Same category
- Similar size (38.4B vs 27B)
- Commercial use OK
ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.
9.7B32K ctx Apache 2.0339.4K 43Apr 2026- Same category
- Smaller (9.7B vs 27B)
- Commercial use OK
Developer: Microsoft Corporation Authorized Representative: Microsoft Ireland Operations Limited, 70 Sir John Rogerson's Quay, Dublin 2, D02 R296, Ireland Release Date: March 4, 2026 License: MIT Parameters: 15B Context Length: 16,384 tokens Inputs: Text and Images Outputs: Text Training GPUs: 240…
15.1B32K ctx MIT9.7K 185Jan 2026- Same category
- Similar size (15.1B vs 27B)
- Commercial use OK
For NEO Imatrix GGUFS - reg and MTP, as well as full model details/card please go here:
40B256K ctx Apache 2.0337 68Jul 2026- Same category
- Similar size (40B vs 27B)
- Commercial use OK
VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios.
10B256K ctx Apache 2.073.4K 42Jul 2026- Same category
- Smaller (10B vs 27B)
- Commercial use OK
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities—all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B).
16.4BA3B128K ctx MIT28.5K 286Apr 2025- Same category
- Similar size (16.4B vs 27B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
9.7B256K ctx Apache 2.0266.8K 163Feb 2026- Same category
- Smaller (9.7B vs 27B)
- Commercial use OK
Skywork-R1V-38B is an open-weight vision model with 38.4B parameters from Skywork, published on Hugging Face.
38.4B128K ctx MIT7.8K 128Mar 2025- Same category
- Similar size (38.4B vs 27B)
- Commercial use OK